Summary for 2021-05-17, created on 2021-12-21

What makes you unique? arxiv:2105.08013 📈 29600

Benjamin B. Seiler, Masayoshi Mase, Art B. Owen

**Abstract:** This paper proposes a uniqueness Shapley measure to compare the extent to which different variables are able to identify a subject. Revealing the value of a variable on subject $t$ shrinks the set of possible subjects that $t$ could be. The extent of the shrinkage depends on which other variables have also been revealed. We use Shapley value to combine all of the reductions in log cardinality due to revealing a variable after some subset of the other variables has been revealed. This uniqueness Shapley measure can be aggregated over subjects where it becomes a weighted sum of conditional entropies. Aggregation over subsets of subjects can address questions like how identifying is age for people of a given zip code. Such aggregates have a corresponding expression in terms of cross entropies. We use uniqueness Shapley to investigate the differential effects of revealing variables from the North Carolina voter registration rolls and in identifying anomalous solar flares. An enormous speedup (approaching 2000 fold in one example) is obtained by using the all dimension trees of Moore and Lee (1998) to store the cardinalities we need.

Pay Attention to MLPs arxiv:2105.08050 📈 286

Hanxiao Liu, Zihang Dai, David R. So, Quoc V. Le

**Abstract:** Transformers have become one of the most important architectural innovations in deep learning and have enabled many breakthroughs over the past few years. Here we propose a simple network architecture, gMLP, based on MLPs with gating, and show that it can perform as well as Transformers in key language and vision applications. Our comparisons show that self-attention is not critical for Vision Transformers, as gMLP can achieve the same accuracy. For BERT, our model achieves parity with Transformers on pretraining perplexity and is better on some downstream NLP tasks. On finetuning tasks where gMLP performs worse, making the gMLP model substantially larger can close the gap with Transformers. In general, our experiments show that gMLP can scale as well as Transformers over increased data and compute.

Continual Learning with Echo State Networks arxiv:2105.07674 📈 40

Andrea Cossu, Davide Bacciu, Antonio Carta, Claudio Gallicchio, Vincenzo Lomonaco

**Abstract:** Continual Learning (CL) refers to a learning setup where data is non stationary and the model has to learn without forgetting existing knowledge. The study of CL for sequential patterns revolves around trained recurrent networks. In this work, instead, we introduce CL in the context of Echo State Networks (ESNs), where the recurrent component is kept fixed. We provide the first evaluation of catastrophic forgetting in ESNs and we highlight the benefits in using CL strategies which are not applicable to trained recurrent models. Our results confirm the ESN as a promising model for CL and open to its use in streaming scenarios.

Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement arxiv:2105.08195 📈 23

Samuel Daulton, Maximilian Balandat, Eytan Bakshy

**Abstract:** Optimizing multiple competing black-box objectives is a challenging problem in many fields, including science, engineering, and machine learning. Multi-objective Bayesian optimization (MOBO) is a sample-efficient approach for identifying the optimal trade-offs between the objectives. However, many existing methods perform poorly when the observations are corrupted by noise. We propose a novel acquisition function, NEHVI, that overcomes this important practical limitation by applying a Bayesian treatment to the popular expected hypervolume improvement (EHVI) criterion and integrating over this uncertainty in the Pareto frontier. We argue that, even in the noiseless setting, generating multiple candidates in parallel is an incarnation of EHVI with uncertainty in the Pareto frontier and therefore can be addressed using the same underlying technique. Through this lens, we derive a natural parallel variant, $q$NEHVI, that reduces computational complexity of parallel EHVI from exponential to polynomial with respect to the batch size. $q$NEHVI is one-step Bayes-optimal for hypervolume maximization in both noisy and noiseless environments, and we show that it can be optimized effectively with gradient-based methods via sample average approximation. Empirically, we demonstrate not only that $q$NEHVI is substantially more robust to observation noise than existing MOBO approaches, but also that it achieves state-of-the-art optimization performance and competitive wall-times in large-batch environments.

OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding arxiv:2105.07688 📈 23

Yuejia Xiang, Ziheng Zhang, Jiaoyan Chen, Xi Chen, Zhenxi Lin, Yefeng Zheng

**Abstract:** Semantic embedding has been widely investigated for aligning knowledge graph (KG) entities. Current methods have explored and utilized the graph structure, the entity names and attributes, but ignore the ontology (or ontological schema) which contains critical meta information such as classes and their membership relationships with entities. In this paper, we propose an ontology-guided entity alignment method named OntoEA, where both KGs and their ontologies are jointly embedded, and the class hierarchy and the class disjointness are utilized to avoid false mappings. Extensive experiments on seven public and industrial benchmarks have demonstrated the state-of-the-art performance of OntoEA and the effectiveness of the ontologies.

Automatic Fake News Detection: Are Models Learning to Reason? arxiv:2105.07698 📈 21

Casper Hansen, Christian Hansen, Lucas Chaves Lima

**Abstract:** Most fact checking models for automatic fake news detection are based on reasoning: given a claim with associated evidence, the models aim to estimate the claim veracity based on the supporting or refuting content within the evidence. When these models perform well, it is generally assumed to be due to the models having learned to reason over the evidence with regards to the claim. In this paper, we investigate this assumption of reasoning, by exploring the relationship and importance of both claim and evidence. Surprisingly, we find on political fact checking datasets that most often the highest effectiveness is obtained by utilizing only the evidence, as the impact of including the claim is either negligible or harmful to the effectiveness. This highlights an important problem in what constitutes evidence in existing approaches for automatic fake news detection.

Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation arxiv:2105.07830 📈 18

Suman Saha, Anton Obukhov, Danda Pani Paudel, Menelaos Kanakis, Yuhua Chen, Stamatios Georgoulis, Luc Van Gool

**Abstract:** We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. Semantic segmentation and monocular depth estimation are shown to be complementary tasks; in a multi-task learning setting, a proper encoding of their relationships can further improve performance on both tasks. Motivated by this observation, we propose a novel Cross-Task Relation Layer (CTRL), which encodes task dependencies between the semantic and depth predictions. To capture the cross-task relationships, we propose a neural network architecture that contains task-specific and cross-task refinement heads. Furthermore, we propose an Iterative Self-Learning (ISL) training scheme, which exploits semantic pseudo-labels to provide extra supervision on the target domain. We experimentally observe improvements in both tasks' performance because the complementary information present in these tasks is better captured. Specifically, we show that: (1) our approach improves performance on all tasks when they are complementary and mutually dependent; (2) the CTRL helps to improve both semantic segmentation and depth estimation tasks performance in the challenging UDA setting; (3) the proposed ISL training scheme further improves the semantic segmentation performance. The implementation is available at https://github.com/susaha/ctrl-uda.

Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics arxiv:2105.08164 📈 14

Vivek Jayaram, John Thickstun

**Abstract:** This paper introduces an alternative approach to sampling from autoregressive models. Autoregressive models are typically sampled sequentially, according to the transition dynamics defined by the model. Instead, we propose a sampling procedure that initializes a sequence with white noise and follows a Markov chain defined by Langevin dynamics on the global log-likelihood of the sequence. This approach parallelizes the sampling process and generalizes to conditional sampling. Using an autoregressive model as a Bayesian prior, we can steer the output of a generative model using a conditional likelihood or constraints. We apply these techniques to autoregressive models in the visual and audio domains, with competitive results for audio source separation, super-resolution, and inpainting.

Learn to Intervene: An Adaptive Learning Policy for Restless Bandits in Application to Preventive Healthcare arxiv:2105.07965 📈 14

Arpita Biswas, Gaurav Aggarwal, Pradeep Varakantham, Milind Tambe

**Abstract:** In many public health settings, it is important for patients to adhere to health programs, such as taking medications and periodic health checks. Unfortunately, beneficiaries may gradually disengage from such programs, which is detrimental to their health. A concrete example of gradual disengagement has been observed by an organization that carries out a free automated call-based program for spreading preventive care information among pregnant women. Many women stop picking up calls after being enrolled for a few months. To avoid such disengagements, it is important to provide timely interventions. Such interventions are often expensive and can be provided to only a small fraction of the beneficiaries. We model this scenario as a restless multi-armed bandit (RMAB) problem, where each beneficiary is assumed to transition from one state to another depending on the intervention. Moreover, since the transition probabilities are unknown a priori, we propose a Whittle index based Q-Learning mechanism and show that it converges to the optimal solution. Our method improves over existing learning-based methods for RMABs on multiple benchmarks from literature and also on the maternal healthcare dataset.

Fast and Accurate Camera Scene Detection on Smartphones arxiv:2105.07869 📈 14

Angeline Pouget, Sidharth Ramesh, Maximilian Giang, Ramithan Chandrapalan, Toni Tanner, Moritz Prussing, Radu Timofte, Andrey Ignatov

**Abstract:** AI-powered automatic camera scene detection mode is nowadays available in nearly any modern smartphone, though the problem of accurate scene prediction has not yet been addressed by the research community. This paper for the first time carefully defines this problem and proposes a novel Camera Scene Detection Dataset (CamSDD) containing more than 11K manually crawled images belonging to 30 different scene categories. We propose an efficient and NPU-friendly CNN model for this task that demonstrates a top-3 accuracy of 99.5% on this dataset and achieves more than 200 FPS on the recent mobile SoCs. An additional in-the-wild evaluation of the obtained solution is performed to analyze its performance and limitation in the real-world scenarios. The dataset and pre-trained models used in this paper are available on the project website.

Explicit Semantic Cross Feature Learning via Pre-trained Graph Neural Networks for CTR Prediction arxiv:2105.07752 📈 13

Feng Li, Bencheng Yan, Qingqing Long, Pengjie Wang, Wei Lin, Jian Xu, Bo Zheng

**Abstract:** Cross features play an important role in click-through rate (CTR) prediction. Most of the existing methods adopt a DNN-based model to capture the cross features in an implicit manner. These implicit methods may lead to a sub-optimized performance due to the limitation in explicit semantic modeling. Although traditional statistical explicit semantic cross features can address the problem in these implicit methods, it still suffers from some challenges, including lack of generalization and expensive memory cost. Few works focus on tackling these challenges. In this paper, we take the first step in learning the explicit semantic cross features and propose Pre-trained Cross Feature learning Graph Neural Networks (PCF-GNN), a GNN based pre-trained model aiming at generating cross features in an explicit fashion. Extensive experiments are conducted on both public and industrial datasets, where PCF-GNN shows competence in both performance and memory-efficiency in various tasks.

Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers arxiv:2105.07957 📈 10

Daniel Tanneberg, Elmar Rueckert, Jan Peters

**Abstract:** A key feature of intelligent behaviour is the ability to learn abstract strategies that scale and transfer to unfamiliar problems. An abstract strategy solves every sample from a problem class, no matter its representation or complexity -- like algorithms in computer science. Neural networks are powerful models for processing sensory data, discovering hidden patterns, and learning complex functions, but they struggle to learn such iterative, sequential or hierarchical algorithmic strategies. Extending neural networks with external memories has increased their capacities in learning such strategies, but they are still prone to data variations, struggle to learn scalable and transferable solutions, and require massive training data. We present the Neural Harvard Computer (NHC), a memory-augmented network based architecture, that employs abstraction by decoupling algorithmic operations from data manipulations, realized by splitting the information flow and separated modules. This abstraction mechanism and evolutionary training enable the learning of robust and scalable algorithmic solutions. On a diverse set of 11 algorithms with varying complexities, we show that the NHC reliably learns algorithmic solutions with strong generalization and abstraction: perfect generalization and scaling to arbitrary task configurations and complexities far beyond seen during training, and being independent of the data representation and the task domain.

PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training arxiv:2105.08128 📈 9

Luke Melas-Kyriazi, Arjun K. Manrai

**Abstract:** Unsupervised domain adaptation is a promising technique for semantic segmentation and other computer vision tasks for which large-scale data annotation is costly and time-consuming. In semantic segmentation, it is attractive to train models on annotated images from a simulated (source) domain and deploy them on real (target) domains. In this work, we present a novel framework for unsupervised domain adaptation based on the notion of target-domain consistency training. Intuitively, our work is based on the idea that in order to perform well on the target domain, a model's output should be consistent with respect to small perturbations of inputs in the target domain. Specifically, we introduce a new loss term to enforce pixelwise consistency between the model's predictions on a target image and a perturbed version of the same image. In comparison to popular adversarial adaptation methods, our approach is simpler, easier to implement, and more memory-efficient during training. Experiments and extensive ablation studies demonstrate that our simple approach achieves remarkably strong results on two challenging synthetic-to-real benchmarks, GTA5-to-Cityscapes and SYNTHIA-to-Cityscapes. Code is available at: https://github.com/lukemelas/pixmatch

A Measure of Research Taste arxiv:2105.08089 📈 9

Vladlen Koltun, David Hafner

**Abstract:** Researchers are often evaluated by citation-based metrics. Such metrics can inform hiring, promotion, and funding decisions. Concerns have been expressed that popular citation-based metrics incentivize researchers to maximize the production of publications. Such incentives may not be optimal for scientific progress. Here we present a citation-based measure that rewards both productivity and taste: the researcher's ability to focus on impactful contributions. The presented measure, CAP, balances the impact of publications and their quantity, thus incentivizing researchers to consider whether a publication is a useful addition to the literature. CAP is simple, interpretable, and parameter-free. We analyze the characteristics of CAP for highly-cited researchers in biology, computer science, economics, and physics, using a corpus of millions of publications and hundreds of millions of citations with yearly temporal granularity. CAP produces qualitatively plausible outcomes and has a number of advantages over prior metrics. Results can be explored at https://cap-measure.org/

Stage-wise Fine-tuning for Graph-to-Text Generation arxiv:2105.08021 📈 9

Qingyun Wang, Semih Yavuz, Victoria Lin, Heng Ji, Nazneen Rajani

**Abstract:** Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper, we aim to further improve the performance of the pre-trained language model by proposing a structured graph-to-text model with a two-step fine-tuning mechanism which first fine-tunes the model on Wikipedia before adapting to the graph-to-text generation. In addition to using the traditional token and position embeddings to encode the knowledge graph (KG), we propose a novel tree-level embedding method to capture the inter-dependency structures of the input graph. This new approach has significantly improved the performance of all text generation metrics for the English WebNLG 2017 dataset.

Mean Field Games Flock! The Reinforcement Learning Way arxiv:2105.07933 📈 9

Sarah Perrin, Mathieu Laurière, Julien Pérolat, Matthieu Geist, Romuald Élie, Olivier Pietquin

**Abstract:** We present a method enabling a large number of agents to learn how to flock, which is a natural behavior observed in large populations of animals. This problem has drawn a lot of interest but requires many structural assumptions and is tractable only in small dimensions. We phrase this problem as a Mean Field Game (MFG), where each individual chooses its acceleration depending on the population behavior. Combining Deep Reinforcement Learning (RL) and Normalizing Flows (NF), we obtain a tractable solution requiring only very weak assumptions. Our algorithm finds a Nash Equilibrium and the agents adapt their velocity to match the neighboring flock's average one. We use Fictitious Play and alternate: (1) computing an approximate best response with Deep RL, and (2) estimating the next population distribution with NF. We show numerically that our algorithm learn multi-group or high-dimensional flocking with obstacles.

Physics-informed attention-based neural network for solving non-linear partial differential equations arxiv:2105.07898 📈 9

Ruben Rodriguez-Torrado, Pablo Ruiz, Luis Cueto-Felgueroso, Michael Cerny Green, Tyler Friesen, Sebastien Matringe, Julian Togelius

**Abstract:** Physics-Informed Neural Networks (PINNs) have enabled significant improvements in modelling physical processes described by partial differential equations (PDEs). PINNs are based on simple architectures, and learn the behavior of complex physical systems by optimizing the network parameters to minimize the residual of the underlying PDE. Current network architectures share some of the limitations of classical numerical discretization schemes when applied to non-linear differential equations in continuum mechanics. A paradigmatic example is the solution of hyperbolic conservation laws that develop highly localized nonlinear shock waves. Learning solutions of PDEs with dominant hyperbolic character is a challenge for current PINN approaches, which rely, like most grid-based numerical schemes, on adding artificial dissipation. Here, we address the fundamental question of which network architectures are best suited to learn the complex behavior of non-linear PDEs. We focus on network architecture rather than on residual regularization. Our new methodology, called Physics-Informed Attention-based Neural Networks, (PIANNs), is a combination of recurrent neural networks and attention mechanisms. The attention mechanism adapts the behavior of the deep neural network to the non-linear features of the solution, and break the current limitations of PINNs. We find that PIANNs effectively capture the shock front in a hyperbolic model problem, and are capable of providing high-quality solutions inside and beyond the training set.

Learning a Latent Simplex in Input-Sparsity Time arxiv:2105.08005 📈 8

Ainesh Bakshi, Chiranjib Bhattacharyya, Ravi Kannan, David P. Woodruff, Samson Zhou

**Abstract:** We consider the problem of learning a latent $k$-vertex simplex $K\subset\mathbb{R}^d$, given access to $A\in\mathbb{R}^{d\times n}$, which can be viewed as a data matrix with $n$ points that are obtained by randomly perturbing latent points in the simplex $K$ (potentially beyond $K$). A large class of latent variable models, such as adversarial clustering, mixed membership stochastic block models, and topic models can be cast as learning a latent simplex. Bhattacharyya and Kannan (SODA, 2020) give an algorithm for learning such a latent simplex in time roughly $O(k\cdot\textrm{nnz}(A))$, where $\textrm{nnz}(A)$ is the number of non-zeros in $A$. We show that the dependence on $k$ in the running time is unnecessary given a natural assumption about the mass of the top $k$ singular values of $A$, which holds in many of these applications. Further, we show this assumption is necessary, as otherwise an algorithm for learning a latent simplex would imply an algorithmic breakthrough for spectral low rank approximation. At a high level, Bhattacharyya and Kannan provide an adaptive algorithm that makes $k$ matrix-vector product queries to $A$ and each query is a function of all queries preceding it. Since each matrix-vector product requires $\textrm{nnz}(A)$ time, their overall running time appears unavoidable. Instead, we obtain a low-rank approximation to $A$ in input-sparsity time and show that the column space thus obtained has small $\sinΘ$ (angular) distance to the right top-$k$ singular space of $A$. Our algorithm then selects $k$ points in the low-rank subspace with the largest inner product with $k$ carefully chosen random vectors. By working in the low-rank subspace, we avoid reading the entire matrix in each iteration and thus circumvent the $Θ(k\cdot\textrm{nnz}(A))$ running time.

Controlling an Inverted Pendulum with Policy Gradient Methods-A Tutorial arxiv:2105.07998 📈 8

Swagat Kumar

**Abstract:** This paper provides the details of implementing two important policy gradient methods to solve the inverted pendulum problem. These are namely the Deep Deterministic Policy Gradient (DDPG) and the Proximal Policy Optimization (PPO) algorithm. The problem is solved by using an actor-critic model where an actor-network is used to learn the policy function and a critic network is to evaluate the actor-network by learning to estimate the Q function. Apart from briefly explaining the mathematics behind these two algorithms, the details of python implementation are provided which helps in demystifying the underlying complexity of the algorithm. In the process, the readers will be introduced to OpenAI/Gym, Tensorflow 2.x and Keras utilities used for implementing the above concepts.

Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning arxiv:2105.07985 📈 8

Franziska Boenisch, Philip Sperl, Konstantin Böttinger

**Abstract:** An important problem in deep learning is the privacy and security of neural networks (NNs). Both aspects have long been considered separately. To date, it is still poorly understood how privacy enhancing training affects the robustness of NNs. This paper experimentally evaluates the impact of training with Differential Privacy (DP), a standard method for privacy preservation, on model vulnerability against a broad range of adversarial attacks. The results suggest that private models are less robust than their non-private counterparts, and that adversarial examples transfer better among DP models than between non-private and private ones. Furthermore, detailed analyses of DP and non-DP models suggest significant differences between their gradients. Additionally, this work is the first to observe that an unfavorable choice of parameters in DP training can lead to gradient masking, and, thereby, results in a wrong sense of security.

TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning arxiv:2105.07944 📈 8

Lu Wang, Xiaofu Chang, Shuang Li, Yunfei Chu, Hui Li, Wei Zhang, Xiaofeng He, Le Song, Jingren Zhou, Hongxia Yang

**Abstract:** Dynamic graph modeling has recently attracted much attention due to its extensive applications in many real-world scenarios, such as recommendation systems, financial transactions, and social networks. Although many works have been proposed for dynamic graph modeling in recent years, effective and scalable models are yet to be developed. In this paper, we propose a novel graph neural network approach, called TCL, which deals with the dynamically-evolving graph in a continuous-time fashion and enables effective dynamic node representation learning that captures both the temporal and topology information. Technically, our model contains three novel aspects. First, we generalize the vanilla Transformer to temporal graph learning scenarios and design a graph-topology-aware transformer. Secondly, on top of the proposed graph transformer, we introduce a two-stream encoder that separately extracts representations from temporal neighborhoods associated with the two interaction nodes and then utilizes a co-attentional transformer to model inter-dependencies at a semantic level. Lastly, we are inspired by the recently developed contrastive learning and propose to optimize our model by maximizing mutual information (MI) between the predictive representations of two future interaction nodes. Benefiting from this, our dynamic representations can preserve high-level (or global) semantics about interactions and thus is robust to noisy interactions. To the best of our knowledge, this is the first attempt to apply contrastive learning to representation learning on dynamic graphs. We evaluate our model on four benchmark datasets for interaction prediction and experiment results demonstrate the superiority of our model.

Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models arxiv:2105.08127 📈 7

Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, Andrea Vedaldi

**Abstract:** Recent research has shown that numerous human-interpretable directions exist in the latent space of GANs. In this paper, we develop an automatic procedure for finding directions that lead to foreground-background image separation, and we use these directions to train an image segmentation model without human supervision. Our method is generator-agnostic, producing strong segmentation results with a wide range of different GAN architectures. Furthermore, by leveraging GANs pretrained on large datasets such as ImageNet, we are able to segment images from a range of domains without further training or finetuning. Evaluating our method on image segmentation benchmarks, we compare favorably to prior work while using neither human supervision nor access to the training data. Broadly, our results demonstrate that automatically extracting foreground-background structure from pretrained deep generative models can serve as a remarkably effective substitute for human supervision.

SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services arxiv:2105.08049 📈 7

Yang Zhang, Vahid Noroozi, Evelina Bakhturina, Boris Ginsburg

**Abstract:** Dialogue state tracking is an essential part of goal-oriented dialogue systems, while most of these state tracking models often fail to handle unseen services. In this paper, we propose SGD-QA, a simple and extensible model for schema-guided dialogue state tracking based on a question answering approach. The proposed multi-pass model shares a single encoder between the domain information and dialogue utterance. The domain's description represents the query and the dialogue utterance serves as the context. The model improves performance on unseen services by at least 1.6x compared to single-pass baseline models on the SGD dataset. SGD-QA shows competitive performance compared to state-of-the-art multi-pass models while being significantly more efficient in terms of memory consumption and training performance. We provide a thorough discussion on the model with ablation study and error analysis.

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting arxiv:2105.08024 📈 7

Gen Li, Yuxin Chen, Yuejie Chi, Yuantao Gu, Yuting Wei

**Abstract:** Low-complexity models such as linear function representation play a pivotal role in enabling sample-efficient reinforcement learning (RL). The current paper pertains to a scenario with value-based linear representation, which postulates the linear realizability of the optimal Q-function (also called the "linear $Q^{\star}$ problem"). While linear realizability alone does not allow for sample-efficient solutions in general, the presence of a large sub-optimality gap is a potential game changer, depending on the sampling mechanism in use. Informally, sample efficiency is achievable with a large sub-optimality gap when a generative model is available but is unfortunately infeasible when we turn to standard online RL settings. In this paper, we make progress towards understanding this linear $Q^{\star}$ problem by investigating a new sampling protocol, which draws samples in an online/exploratory fashion but allows one to backtrack and revisit previous states in a controlled and infrequent manner. This protocol is more flexible than the standard online RL setting, while being practically relevant and far more restrictive than the generative model. We develop an algorithm tailored to this setting, achieving a sample complexity that scales polynomially with the feature dimension, the horizon, and the inverse sub-optimality gap, but not the size of the state/action space. Our findings underscore the fundamental interplay between sampling protocols and low-complexity structural representation in RL.

Removing Data Heterogeneity Influence Enhances Network Topology Dependence of Decentralized SGD arxiv:2105.08023 📈 7

Kun Yuan, Sulaiman A. Alghunaim

**Abstract:** We consider decentralized stochastic optimization problems where a network of agents each owns a local cost function cooperate to find a minimizer of the global-averaged cost. A widely studied decentralized algorithm for this problem is D-SGD in which each node applies a stochastic gradient descent step, then averages its estimate with its neighbors. D-SGD is attractive due to its efficient single-iteration communication and can achieve linear speedup in convergence (in terms of the network size). However, D-SGD is very sensitive to the network topology. For smooth objective functions, the transient stage (which measures how fast the algorithm can reach the linear speedup stage) of D-SGD is on the order of $O(n/(1-β)^2)$ and $O(n^3/(1-β)^4)$ for strongly convex and generally convex cost functions, respectively, where $1-β\in (0,1)$ is a topology-dependent quantity that approaches $0$ for a large and sparse network. Hence, D-SGD suffers from slow convergence for large and sparse networks. In this work, we study the non-asymptotic convergence property of the D$^2$/Exact-diffusion algorithm. By eliminating the influence of data heterogeneity between nodes, D$^2$/Exact-diffusion is shown to have an enhanced transient stage that are on the order of $O(n/(1-β))$ and $O(n^3/(1-β)^2)$ for strongly convex and generally convex cost functions, respectively. Moreover, we provide a lower bound of the transient stage of D-SGD under homogeneous data distributions, which coincides with the transient stage of D$^2$/Exact-diffusion in the strongly-convex setting. These results show that removing the influence of data heterogeneity can ameliorate the network topology dependence of D-SGD. Compared with existing decentralized algorithms bounds, D$^2$/Exact-diffusion is least sensitive to network topology.

Supporting Context Monotonicity Abstractions in Neural NLI Models arxiv:2105.08008 📈 7

Julia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan, Marco Valentino, André Freitas

**Abstract:** Natural language contexts display logical regularities with respect to substitutions of related concepts: these are captured in a functional order-theoretic property called monotonicity. For a certain class of NLI problems where the resulting entailment label depends only on the context monotonicity and the relation between the substituted concepts, we build on previous techniques that aim to improve the performance of NLI models for these problems, as consistent performance across both upward and downward monotone contexts still seems difficult to attain even for state-of-the-art models. To this end, we reframe the problem of context monotonicity classification to make it compatible with transformer-based pre-trained NLI models and add this task to the training pipeline. Furthermore, we introduce a sound and complete simplified monotonicity logic formalism which describes our treatment of contexts as abstract units. Using the notions in our formalism, we adapt targeted challenge sets to investigate whether an intermediate context monotonicity classification task can aid NLI models' performance on examples exhibiting monotonicity reasoning.

CNN-based Approaches For Cross-Subject Classification in Motor Imagery: From The State-of-The-Art to DynamicNet arxiv:2105.07917 📈 7

Alberto Zancanaro, Giulia Cisotto, João Ruivo Paulo, Gabriel Pires, Urbano J. Nunes

**Abstract:** Motor imagery (MI)-based brain-computer interface (BCI) systems are being increasingly employed to provide alternative means of communication and control for people suffering from neuro-motor impairments, with a special effort to bring these systems out of the controlled lab environments. Hence, accurately classifying MI from brain signals, e.g., from electroencephalography (EEG), is essential to obtain reliable BCI systems. However, MI classification is still a challenging task, because the signals are characterized by poor SNR, high intra-subject and cross-subject variability. Deep learning approaches have started to emerge as valid alternatives to standard machine learning techniques, e.g., filter bank common spatial pattern (FBCSP), to extract subject-independent features and to increase the cross-subject classification performance of MI BCI systems. In this paper, we first present a review of the most recent studies using deep learning for MI classification, with particular attention to their cross-subject performance. Second, we propose DynamicNet, a Python-based tool for quick and flexible implementations of deep learning models based on convolutional neural networks. We show-case the potentiality of DynamicNet by implementing EEGNet, a well-established architecture for effective EEG classification. Finally, we compare its performance with FBCSP in a 4-class MI classification over public datasets. To explore its cross-subject classification ability, we applied three different cross-validation schemes. From our results, we demonstrate that DynamicNet-implemented EEGNet outperforms FBCSP by about 25%, with a statistically significant difference when cross-subject validation schemes are applied.

Towards a Better Tradeoff between Effectiveness and Efficiency in Pre-Ranking: A Learnable Feature Selection based Approach arxiv:2105.07706 📈 7

Xu Ma, Pengjie Wang, Hui Zhao, Shaoguo Liu, Chuhan Zhao, Wei Lin, Kuang-Chih Lee, Jian Xu, Bo Zheng

**Abstract:** In real-world search, recommendation, and advertising systems, the multi-stage ranking architecture is commonly adopted. Such architecture usually consists of matching, pre-ranking, ranking, and re-ranking stages. In the pre-ranking stage, vector-product based models with representation-focused architecture are commonly adopted to account for system efficiency. However, it brings a significant loss to the effectiveness of the system. In this paper, a novel pre-ranking approach is proposed which supports complicated models with interaction-focused architecture. It achieves a better tradeoff between effectiveness and efficiency by utilizing the proposed learnable Feature Selection method based on feature Complexity and variational Dropout (FSCD). Evaluations in a real-world e-commerce sponsored search system for a search engine demonstrate that utilizing the proposed pre-ranking, the effectiveness of the system is significantly improved. Moreover, compared to the systems with conventional pre-ranking models, an identical amount of computational resource is consumed.

TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance arxiv:2105.07624 📈 7

Fengbin Zhu, Wenqiang Lei, Youcheng Huang, Chao Wang, Shuo Zhang, Jiancheng Lv, Fuli Feng, Tat-Seng Chua

**Abstract:** Hybrid data combining both tabular and textual content (e.g., financial reports) are quite pervasive in the real world. However, Question Answering (QA) over such hybrid data is largely neglected in existing research. In this work, we extract samples from real financial reports to build a new large-scale QA dataset containing both Tabular And Textual data, named TAT-QA, where numerical reasoning is usually required to infer the answer, such as addition, subtraction, multiplication, division, counting, comparison/sorting, and the compositions. We further propose a novel QA model termed TAGOP, which is capable of reasoning over both tables and text. It adopts sequence tagging to extract relevant cells from the table along with relevant spans from the text to infer their semantics, and then applies symbolic reasoning over them with a set of aggregation operators to arrive at the final answer. TAGOPachieves 58.0% inF1, which is an 11.1% absolute increase over the previous best baseline model, according to our experiments on TAT-QA. But this result still lags far behind performance of expert human, i.e.90.8% in F1. It is demonstrated that our TAT-QA is very challenging and can serve as a benchmark for training and testing powerful QA models that address hybrid form data.

SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising arxiv:2105.07911 📈 6

Kuan Xuan, Yongbo Wang, Yongliang Wang, Zujie Wen, Yang Dong

**Abstract:** In text-to-SQL task, seq-to-seq models often lead to sub-optimal performance due to limitations in their architecture. In this paper, we present a simple yet effective approach that adapts transformer-based seq-to-seq model to robust text-to-SQL generation. Instead of inducing constraint to decoder or reformat the task as slot-filling, we propose to train seq-to-seq model with Schema aware Denoising (SeaD), which consists of two denoising objectives that train model to either recover input or predict output from two novel erosion and shuffle noises. These denoising objectives acts as the auxiliary tasks for better modeling the structural data in S2S generation. In addition, we improve and propose a clause-sensitive execution guided (EG) decoding strategy to overcome the limitation of EG decoding for generative model. The experiments show that the proposed method improves the performance of seq-to-seq model in both schema linking and grammar correctness and establishes new state-of-the-art on WikiSQL benchmark. The results indicate that the capacity of vanilla seq-to-seq architecture for text-to-SQL may have been under-estimated.

Towards Demystifying Serverless Machine Learning Training arxiv:2105.07806 📈 6

Jiawei Jiang, Shaoduo Gan, Yue Liu, Fanlin Wang, Gustavo Alonso, Ana Klimovic, Ankit Singla, Wentao Wu, Ce Zhang

**Abstract:** The appeal of serverless (FaaS) has triggered a growing interest on how to use it in data-intensive applications such as ETL, query processing, or machine learning (ML). Several systems exist for training large-scale ML models on top of serverless infrastructures (e.g., AWS Lambda) but with inconclusive results in terms of their performance and relative advantage over "serverful" infrastructures (IaaS). In this paper we present a systematic, comparative study of distributed ML training over FaaS and IaaS. We present a design space covering design choices such as optimization algorithms and synchronization protocols, and implement a platform, LambdaML, that enables a fair comparison between FaaS and IaaS. We present experimental results using LambdaML, and further develop an analytic model to capture cost/performance tradeoffs that must be considered when opting for a serverless infrastructure. Our results indicate that ML training pays off in serverless only for models with efficient (i.e., reduced) communication and that quickly converge. In general, FaaS can be much faster but it is never significantly cheaper than IaaS.

Improving Graph Neural Networks with Simple Architecture Design arxiv:2105.07634 📈 6

Sunil Kumar Maurya, Xin Liu, Tsuyoshi Murata

**Abstract:** Graph Neural Networks have emerged as a useful tool to learn on the data by applying additional constraints based on the graph structure. These graphs are often created with assumed intrinsic relations between the entities. In recent years, there have been tremendous improvements in the architecture design, pushing the performance up in various prediction tasks. In general, these neural architectures combine layer depth and node feature aggregation steps. This makes it challenging to analyze the importance of features at various hops and the expressiveness of the neural network layers. As different graph datasets show varying levels of homophily and heterophily in features and class label distribution, it becomes essential to understand which features are important for the prediction tasks without any prior information. In this work, we decouple the node feature aggregation step and depth of graph neural network and introduce several key design strategies for graph neural networks. More specifically, we propose to use softmax as a regularizer and "Soft-Selector" of features aggregated from neighbors at different hop distances; and "Hop-Normalization" over GNN layers. Combining these techniques, we present a simple and shallow model, Feature Selection Graph Neural Network (FSGNN), and show empirically that the proposed model outperforms other state of the art GNN models and achieves up to 64% improvements in accuracy on node classification tasks. Moreover, analyzing the learned soft-selection parameters of the model provides a simple way to study the importance of features in the prediction tasks. Finally, we demonstrate with experiments that the model is scalable for large graphs with millions of nodes and billions of edges.

Social Behavior and Mental Health: A Snapshot Survey under COVID-19 Pandemic arxiv:2105.08165 📈 5

Sahraoui Dhelim, Liming Luke Chen, Huansheng Ning, Sajal K Das, Chris Nugent, Devin Burns, Gerard Leavey, Dirk Pesch, Eleanor Bantry-White

**Abstract:** Online social media provides a channel for monitoring people's social behaviors and their mental distress. Due to the restrictions imposed by COVID-19 people are increasingly using online social networks to express their feelings. Consequently, there is a significant amount of diverse user-generated social media content. However, COVID-19 pandemic has changed the way we live, study, socialize and recreate and this has affected our well-being and mental health problems. There are growing researches that leverage online social media analysis to detect and assess user's mental status. In this paper, we survey the literature of social media analysis for mental disorders detection, with a special focus on the studies conducted in the context of COVID-19 during 2020-2021. Firstly, we classify the surveyed studies in terms of feature extraction types, varying from language usage patterns to aesthetic preferences and online behaviors. Secondly, we explore detection methods used for mental disorders detection including machine learning and deep learning detection methods. Finally, we discuss the challenges of mental disorder detection using social media data, including the privacy and ethical concerns, as well as the technical challenges of scaling and deploying such systems at large scales, and discuss the learnt lessons over the last few years.

VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living arxiv:2105.08141 📈 5

Srijan Das, Rui Dai, Di Yang, Francois Bremond

**Abstract:** Many attempts have been made towards combining RGB and 3D poses for the recognition of Activities of Daily Living (ADL). ADL may look very similar and often necessitate to model fine-grained details to distinguish them. Because the recent 3D ConvNets are too rigid to capture the subtle visual patterns across an action, this research direction is dominated by methods combining RGB and 3D Poses. But the cost of computing 3D poses from RGB stream is high in the absence of appropriate sensors. This limits the usage of aforementioned approaches in real-world applications requiring low latency. Then, how to best take advantage of 3D Poses for recognizing ADL? To this end, we propose an extension of a pose driven attention mechanism: Video-Pose Network (VPN), exploring two distinct directions. One is to transfer the Pose knowledge into RGB through a feature-level distillation and the other towards mimicking pose driven attention through an attention-level distillation. Finally, these two approaches are integrated into a single model, we call VPN++. We show that VPN++ is not only effective but also provides a high speed up and high resilience to noisy Poses. VPN++, with or without 3D Poses, outperforms the representative baselines on 4 public datasets. Code is available at https://github.com/srijandas07/vpnplusplus.

Learning to Automatically Catch Potholes in Worldwide Road Scene Images arxiv:2105.07986 📈 5

J. Javier Yebes, David Montero, Ignacio Arriola

**Abstract:** Among several road hazards that are present in any paved way in the world, potholes are one of the most annoying and also involving higher maintenance costs. There exists an increasing interest on the automated detection of these hazards enabled by technological and research progress. Our research work tackled the challenge of pothole detection from images of real world road scenes. The main novelty resides on the application of the latest progress in AI to learn the visual appearance of potholes. We built a large dataset of images with pothole annotations. They contained road scenes from different cities in the world, taken with different cameras, vehicles and viewpoints under varied environmental conditions. Then, we fine-tuned four different object detection models based on Faster R-CNN and SSD deep neural networks. We achieved high average precision and the pothole detector was tested on the Nvidia DrivePX2 platform with GPGPU capability, which can be embedded on vehicles. Moreover, it was deployed on a real vehicle to notify the detected potholes to a given IoT platform as part of AUTOPILOT H2020 project.

Temporal Prediction and Evaluation of Brassica Growth in the Field using Conditional Generative Adversarial Networks arxiv:2105.07789 📈 5

Lukas Drees, Laura Verena Junker-Frohn, Jana Kierdorf, Ribana Roscher

**Abstract:** Farmers frequently assess plant growth and performance as basis for making decisions when to take action in the field, such as fertilization, weed control, or harvesting. The prediction of plant growth is a major challenge, as it is affected by numerous and highly variable environmental factors. This paper proposes a novel monitoring approach that comprises high-throughput imaging sensor measurements and their automatic analysis to predict future plant growth. Our approach's core is a novel machine learning-based growth model based on conditional generative adversarial networks, which is able to predict the future appearance of individual plants. In experiments with RGB time-series images of laboratory-grown Arabidopsis thaliana and field-grown cauliflower plants, we show that our approach produces realistic, reliable, and reasonable images of future growth stages. The automatic interpretation of the generated images through neural network-based instance segmentation allows the derivation of various phenotypic traits that describe plant growth.

DOC3-Deep One Class Classification using Contradictions arxiv:2105.07636 📈 5

Sauptik Dhar, Bernardo Gonzalez Torres

**Abstract:** This paper introduces the notion of learning from contradictions (a.k.a Universum learning) for deep one class classification problems. We formalize this notion for the widely adopted one class large-margin loss, and propose the Deep One Class Classification using Contradictions (DOC3) algorithm. We show that learning from contradictions incurs lower generalization error by comparing the Empirical Radamacher Complexity (ERC) of DOC3 against its traditional inductive learning counterpart. Our empirical results demonstrate the efficacy of DOC3 algorithm achieving > 30% for CIFAR-10 and >50% for MV-Tec AD data sets in test AUCs compared to its inductive learning counterpart and in many cases improving the state-of-the-art in anomaly detection.

Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report arxiv:2105.08826 📈 4

Andrey Ignatov, Andres Romero, Heewon Kim, Radu Timofte, Chiu Man Ho, Zibo Meng, Kyoung Mu Lee, Yuxiang Chen, Yutong Wang, Zeyu Long, Chenhao Wang, Yifei Chen, Boshen Xu, Shuhang Gu, Lixin Duan, Wen Li, Wang Bofei, Zhang Diankai, Zheng Chengjian, Liu Shaoli, Gao Si, Zhang Xiaofeng, Lu Kaidi, Xu Tianyu, Zheng Hui

**Abstract:** Video super-resolution has recently become one of the most important mobile-related problems due to the rise of video communication and streaming services. While many solutions have been proposed for this task, the majority of them are too computationally expensive to run on portable devices with limited hardware resources. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based video super-resolution solutions that can achieve a real-time performance on mobile GPUs. The participants were provided with the REDS dataset and trained their models to do an efficient 4X video upscaling. The runtime of all models was evaluated on the OPPO Find X2 smartphone with the Snapdragon 865 SoC capable of accelerating floating-point networks on its Adreno GPU. The proposed solutions are fully compatible with any mobile GPU and can upscale videos to HD resolution at up to 80 FPS while demonstrating high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.

Transfer Learning Enhanced Generative Adversarial Networks for Multi-Channel MRI Reconstruction arxiv:2105.08175 📈 4

Jun Lv, Guangyuan Li, Xiangrong Tong, Weibo Chen, Jiahao Huang, Chengyan Wang, Guang Yang

**Abstract:** Deep learning based generative adversarial networks (GAN) can effectively perform image reconstruction with under-sampled MR data. In general, a large number of training samples are required to improve the reconstruction performance of a certain model. However, in real clinical applications, it is difficult to obtain tens of thousands of raw patient data to train the model since saving k-space data is not in the routine clinical flow. Therefore, enhancing the generalizability of a network based on small samples is urgently needed. In this study, three novel applications were explored based on parallel imaging combined with the GAN model (PI-GAN) and transfer learning. The model was pre-trained with public Calgary brain images and then fine-tuned for use in (1) patients with tumors in our center; (2) different anatomies, including knee and liver; (3) different k-space sampling masks with acceleration factors (AFs) of 2 and 6. As for the brain tumor dataset, the transfer learning results could remove the artifacts found in PI-GAN and yield smoother brain edges. The transfer learning results for the knee and liver were superior to those of the PI-GAN model trained with its own dataset using a smaller number of training cases. However, the learning procedure converged more slowly in the knee datasets compared to the learning in the brain tumor datasets. The reconstruction performance was improved by transfer learning both in the models with AFs of 2 and 6. Of these two models, the one with AF=2 showed better results. The results also showed that transfer learning with the pre-trained model could solve the problem of inconsistency between the training and test datasets and facilitate generalization to unseen data.

COVID-19 Lung Lesion Segmentation Using a Sparsely Supervised Mask R-CNN on Chest X-rays Automatically Computed from Volumetric CTs arxiv:2105.08147 📈 4

Vignav Ramesh, Blaine Rister, Daniel L. Rubin

**Abstract:** Chest X-rays of coronavirus disease 2019 (COVID-19) patients are frequently obtained to determine the extent of lung disease and are a valuable source of data for creating artificial intelligence models. Most work to date assessing disease severity on chest imaging has focused on segmenting computed tomography (CT) images; however, given that CTs are performed much less frequently than chest X-rays for COVID-19 patients, automated lung lesion segmentation on chest X-rays could be clinically valuable. There currently exists a universal shortage of chest X-rays with ground truth COVID-19 lung lesion annotations, and manually contouring lung opacities is a tedious, labor-intensive task. To accelerate severity detection and augment the amount of publicly available chest X-ray training data for supervised deep learning (DL) models, we leverage existing annotated CT images to generate frontal projection "chest X-ray" images for training COVID-19 chest X-ray models. In this paper, we propose an automated pipeline for segmentation of COVID-19 lung lesions on chest X-rays comprised of a Mask R-CNN trained on a mixed dataset of open-source chest X-rays and coronal X-ray projections computed from annotated volumetric CTs. On a test set containing 40 chest X-rays of COVID-19 positive patients, our model achieved IoU scores of 0.81 $\pm$ 0.03 and 0.79 $\pm$ 0.03 when trained on a dataset of 60 chest X-rays and on a mixed dataset of 10 chest X-rays and 50 projections from CTs, respectively. Our model far outperforms current baselines with limited supervised training and may assist in automated COVID-19 severity quantification on chest X-rays.

Compressed Communication for Distributed Training: Adaptive Methods and System arxiv:2105.07829 📈 4

Yuchen Zhong, Cong Xie, Shuai Zheng, Haibin Lin

**Abstract:** Communication overhead severely hinders the scalability of distributed machine learning systems. Recently, there has been a growing interest in using gradient compression to reduce the communication overhead of the distributed training. However, there is little understanding of applying gradient compression to adaptive gradient methods. Moreover, its performance benefits are often limited by the non-negligible compression overhead. In this paper, we first introduce a novel adaptive gradient method with gradient compression. We show that the proposed method has a convergence rate of $\mathcal{O}(1/\sqrt{T})$ for non-convex problems. In addition, we develop a scalable system called BytePS-Compress for two-way compression, where the gradients are compressed in both directions between workers and parameter servers. BytePS-Compress pipelines the compression and decompression on CPUs and achieves a high degree of parallelism. Empirical evaluations show that we improve the training time of ResNet50, VGG16, and BERT-base by 5.0%, 58.1%, 23.3%, respectively, without any accuracy loss with 25 Gb/s networking. Furthermore, for training the BERT models, we achieve a compression rate of 333x compared to the mixed-precision training.

TopicsRanksDC: Distance-based Topic Ranking applied on Two-Class Data arxiv:2105.07826 📈 4

Malik Yousef, Jamal Al Qundus, Silvio Peikert, Adrian Paschke

**Abstract:** In this paper, we introduce a novel approach named TopicsRanksDC for topics ranking based on the distance between two clusters that are generated by each topic. We assume that our data consists of text documents that are associated with two-classes. Our approach ranks each topic contained in these text documents by its significance for separating the two-classes. Firstly, the algorithm detects topics using Latent Dirichlet Allocation (LDA). The words defining each topic are represented as two clusters, where each one is associated with one of the classes. We compute four distance metrics, Single Linkage, Complete Linkage, Average Linkage and distance between the centroid. We compare the results of LDA topics and random topics. The results show that the rank for LDA topics is much higher than random topics. The results of TopicsRanksDC tool are promising for future work to enable search engines to suggest related topics.

Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report arxiv:2105.07825 📈 4

Andrey Ignatov, Radu Timofte, Maurizio Denna, Abdel Younes, Andrew Lek, Mustafa Ayazoglu, Jie Liu, Zongcai Du, Jiaming Guo, Xueyi Zhou, Hao Jia, Youliang Yan, Zexin Zhang, Yixin Chen, Yunbo Peng, Yue Lin, Xindong Zhang, Hui Zeng, Kun Zeng, Peirong Li, Zhihuang Liu, Shiqi Xue, Shengpeng Wang

**Abstract:** Image super-resolution is one of the most popular computer vision problems with many important applications to mobile devices. While many solutions have been proposed for this task, they are usually not optimized even for common smartphone AI hardware, not to mention more constrained smart TV platforms that are often supporting INT8 inference only. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based image super-resolution solutions that can demonstrate a real-time performance on mobile or edge NPUs. For this, the participants were provided with the DIV2K dataset and trained quantized models to do an efficient 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated NPU capable of accelerating quantized neural networks. The proposed solutions are fully compatible with all major mobile AI accelerators and are capable of reconstructing Full HD images under 40-60 ms while achieving high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.

Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report arxiv:2105.07809 📈 4

Andrey Ignatov, Cheng-Ming Chiang, Hsien-Kai Kuo, Anastasia Sycheva, Radu Timofte, Min-Hung Chen, Man-Yu Lee, Yu-Syuan Xu, Yu Tseng, Shusong Xu, Jin Guo, Chao-Hung Chen, Ming-Chun Hsyu, Wen-Chia Tsai, Chao-Wei Chen, Grigory Malivenko, Minsu Kwon, Myungje Lee, Jaeyoon Yoo, Changbeom Kang, Shinjo Wang, Zheng Shaolong, Hao Dejun, Xie Fen, Feng Zhuang

**Abstract:** As the quality of mobile cameras starts to play a crucial role in modern smartphones, more and more attention is now being paid to ISP algorithms used to improve various perceptual aspects of mobile photos. In this Mobile AI challenge, the target was to develop an end-to-end deep learning-based image signal processing (ISP) pipeline that can replace classical hand-crafted ISPs and achieve nearly real-time performance on smartphone NPUs. For this, the participants were provided with a novel learned ISP dataset consisting of RAW-RGB image pairs captured with the Sony IMX586 Quad Bayer mobile sensor and a professional 102-megapixel medium format camera. The runtime of all models was evaluated on the MediaTek Dimensity 1000+ platform with a dedicated AI processing unit capable of accelerating both floating-point and quantized neural networks. The proposed solutions are fully compatible with the above NPU and are capable of processing Full HD photos under 60-100 milliseconds while achieving high fidelity results. A detailed description of all models developed in this challenge is provided in this paper.

Classifying variety of customer's online engagement for churn prediction with mixed-penalty logistic regression arxiv:2105.07671 📈 4

Petra Posedel Šimović, Davor Horvatic, Edward W. Sun

**Abstract:** Using big data to analyze consumer behavior can provide effective decision-making tools for preventing customer attrition (churn) in customer relationship management (CRM). Focusing on a CRM dataset with several different categories of factors that impact customer heterogeneity (i.e., usage of self-care service channels, duration of service, and responsiveness to marketing actions), we provide new predictive analytics of customer churn rate based on a machine learning method that enhances the classification of logistic regression by adding a mixed penalty term. The proposed penalized logistic regression can prevent overfitting when dealing with big data and minimize the loss function when balancing the cost from the median (absolute value) and mean (squared value) regularization. We show the analytical properties of the proposed method and its computational advantage in this research. In addition, we investigate the performance of the proposed method with a CRM data set (that has a large number of features) under different settings by efficiently eliminating the disturbance of (1) least important features and (2) sensitivity from the minority (churn) class. Our empirical results confirm the expected performance of the proposed method in full compliance with the common classification criteria (i.e., accuracy, precision, and recall) for evaluating machine learning methods.

Cross-Cluster Weighted Forests arxiv:2105.07610 📈 4

Maya Ramchandran, Rajarshi Mukherjee, Giovanni Parmigiani

**Abstract:** Adapting machine learning algorithms to better handle clustering or batch effects within training data sets is important across a wide variety of biological applications. This article considers the effect of ensembling Random Forest learners trained on clusters within a single data set with heterogeneity in the distribution of the features. We find that constructing ensembles of forests trained on clusters determined by algorithms such as k-means results in significant improvements in accuracy and generalizability over the traditional Random Forest algorithm. We denote our novel approach as the Cross-Cluster Weighted Forest, and examine its robustness to various data-generating scenarios and outcome models. Furthermore, we explore the influence of the data-partitioning and ensemble weighting strategies the benefits of our method over the existing paradigm. Finally, we apply our approach to cancer molecular profiling and gene expression data sets that are naturally divisible into clusters and illustrate that our approach outperforms classic Random Forest. Code and supplementary material are available at https://github.com/m-ramchandran/cross-cluster.

Understanding the Performance of Knowledge Graph Embeddings in Drug Discovery arxiv:2105.10488 📈 3

Stephen Bonner, Ian P Barrett, Cheng Ye, Rowan Swiers, Ola Engkvist, Charles Tapley Hoyt, William L Hamilton

**Abstract:** Knowledge Graphs (KG) and associated Knowledge Graph Embedding (KGE) models have recently begun to be explored in the context of drug discovery and have the potential to assist in key challenges such as target identification. In the drug discovery domain, KGs can be employed as part of a process which can result in lab-based experiments being performed, or impact on other decisions, incurring significant time and financial costs and most importantly, ultimately influencing patient healthcare. For KGE models to have impact in this domain, a better understanding of not only of performance, but also the various factors which determine it, is required. In this study we investigate, over the course of many thousands of experiments, the predictive performance of five KGE models on two public drug discovery-oriented KGs. Our goal is not to focus on the best overall model or configuration, instead we take a deeper look at how performance can be affected by changes in the training setup, choice of hyperparameters, model parameter initialisation seed and different splits of the datasets. Our results highlight that these factors have significant impact on performance and can even affect the ranking of models. Indeed these factors should be reported along with model architectures to ensure complete reproducibility and fair comparisons of future work, and we argue this is critical for the acceptance of use, and impact of KGEs in a biomedical setting. To aid reproducibility of our own work, we release all experimentation code.

Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report arxiv:2105.08819 📈 3

Andrey Ignatov, Grigory Malivenko, Radu Timofte, Sheng Chen, Xin Xia, Zhaoyan Liu, Yuwei Zhang, Feng Zhu, Jiashi Li, Xuefeng Xiao, Yuan Tian, Xinglong Wu, Christos Kyrkou, Yixin Chen, Zexin Zhang, Yunbo Peng, Yue Lin, Saikat Dutta, Sourya Dipta Das, Nisarg A. Shah, Himanshu Kumar, Chao Ge, Pei-Lin Wu, Jin-Hua Du, Andrew Batutin

**Abstract:** Camera scene detection is among the most popular computer vision problem on smartphones. While many custom solutions were developed for this task by phone vendors, none of the designed models were available publicly up until now. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions that can demonstrate a real-time performance on smartphones and IoT platforms. For this, the participants were provided with a large-scale CamSDD dataset consisting of more than 11K images belonging to the 30 most important scene categories. The runtime of all models was evaluated on the popular Apple Bionic A11 platform that can be found in many iOS devices. The proposed solutions are fully compatible with all major mobile AI accelerators and can demonstrate more than 100-200 FPS on the majority of recent smartphone platforms while achieving a top-3 accuracy of more than 98%. A detailed description of all models developed in the challenge is provided in this paper.

Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report arxiv:2105.08629 📈 3

Andrey Ignatov, Kim Byeoung-su, Radu Timofte, Angeline Pouget, Fenglong Song, Cheng Li, Shuai Xiao, Zhongqian Fu, Matteo Maggioni, Yibin Huang, Shen Cheng, Xin Lu, Yifeng Zhou, Liangyu Chen, Donghao Liu, Xiangyu Zhang, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Minsu Kwon, Myungje Lee, Jaeyoon Yoo, Changbeom Kang, Shinjo Wang, Bin Huang

**Abstract:** Image denoising is one of the most critical problems in mobile photo processing. While many solutions have been proposed for this task, they are usually working with synthetic data and are too computationally expensive to run on mobile devices. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based image denoising solution that can demonstrate high efficiency on smartphone GPUs. For this, the participants were provided with a novel large-scale dataset consisting of noisy-clean image pairs captured in the wild. The runtime of all models was evaluated on the Samsung Exynos 2100 chipset with a powerful Mali GPU capable of accelerating floating-point and quantized neural networks. The proposed solutions are fully compatible with any mobile GPU and are capable of processing 480p resolution images under 40-80 ms while achieving high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.

Deep Multistage Multi-Task Learning for Quality Prediction of Multistage Manufacturing Systems arxiv:2105.08180 📈 3

Hao Yan, Nurretin Dorukhan Sergin, William A. Brenneman, Stephen Joseph Lange, Shan Ba

**Abstract:** In multistage manufacturing systems, modeling multiple quality indices based on the process sensing variables is important. However, the classic modeling technique predicts each quality variable one at a time, which fails to consider the correlation within or between stages. We propose a deep multistage multi-task learning framework to jointly predict all output sensing variables in a unified end-to-end learning framework according to the sequential system architecture in the MMS. Our numerical studies and real case study have shown that the new model has a superior performance compared to many benchmark methods as well as great interpretability through developed variable selection techniques.

The Confluence of Networks, Games and Learning arxiv:2105.08158 📈 3

Tao Li, Guanze Peng, Quanyan Zhu, Tamer Basar

**Abstract:** Recent years have witnessed significant advances in technologies and services in modern network applications, including smart grid management, wireless communication, cybersecurity as well as multi-agent autonomous systems. Considering the heterogeneous nature of networked entities, emerging network applications call for game-theoretic models and learning-based approaches in order to create distributed network intelligence that responds to uncertainties and disruptions in a dynamic or an adversarial environment. This paper articulates the confluence of networks, games and learning, which establishes a theoretical underpinning for understanding multi-agent decision-making over networks. We provide an selective overview of game-theoretic learning algorithms within the framework of stochastic approximation theory, and associated applications in some representative contexts of modern network systems, such as the next generation wireless communication networks, the smart grid and distributed machine learning. In addition to existing research works on game-theoretic learning over networks, we highlight several new angles and research endeavors on learning in games that are related to recent developments in artificial intelligence. Some of the new angles extrapolate from our own research interests. The overall objective of the paper is to provide the reader a clear picture of the strengths and challenges of adopting game-theoretic learning methods within the context of network systems, and further to identify fruitful future research directions on both theoretical and applied studies.

Cardiac Functional Analysis with Cine MRI via Deep Learning Reconstruction arxiv:2105.08157 📈 3

Eric Z. Chen, Xiao Chen, Jingyuan Lyu, Qi Liu, Zhongqi Zhang, Yu Ding, Shuheng Zhang, Terrence Chen, Jian Xu, Shanhui Sun

**Abstract:** Retrospectively gated cine (retro-cine) MRI is the clinical standard for cardiac functional analysis. Deep learning (DL) based methods have been proposed for the reconstruction of highly undersampled MRI data and show superior image quality and magnitude faster reconstruction time than CS-based methods. Nevertheless, it remains unclear whether DL reconstruction is suitable for cardiac function analysis. To address this question, in this study we evaluate and compare the cardiac functional values (EDV, ESV and EF for LV and RV, respectively) obtained from highly accelerated MRI acquisition using DL based reconstruction algorithm (DL-cine) with values from CS-cine and conventional retro-cine. To the best of our knowledge, this is the first work to evaluate the cine MRI with deep learning reconstruction for cardiac function analysis and compare it with other conventional methods. The cardiac functional values obtained from cine MRI with deep learning reconstruction are consistent with values from clinical standard retro-cine MRI.

Neural Error Mitigation of Near-Term Quantum Simulations arxiv:2105.08086 📈 3

Elizabeth R. Bennewitz, Florian Hopfmueller, Bohdan Kulchytskyy, Juan Carrasquilla, Pooya Ronagh

**Abstract:** One of the promising applications of early quantum computers is the simulation of quantum systems. Variational methods for near-term quantum computers, such as the variational quantum eigensolver (VQE), are a promising approach to finding ground states of quantum systems relevant in physics, chemistry, and materials science. These approaches, however, are constrained by the effects of noise as well as the limited quantum resources of near-term quantum hardware, motivating the need for quantum error mitigation techniques to reduce the effects of noise. Here we introduce $\textit{neural error mitigation}$, a novel method that uses neural networks to improve estimates of ground states and ground-state observables obtained using VQE on near-term quantum computers. To demonstrate our method's versatility, we apply neural error mitigation to finding the ground states of H$_2$ and LiH molecular Hamiltonians, as well as the lattice Schwinger model. Our results show that neural error mitigation improves the numerical and experimental VQE computation to yield low-energy errors, low infidelities, and accurate estimations of more-complex observables like order parameters and entanglement entropy, without requiring additional quantum resources. Additionally, neural error mitigation is agnostic to both the quantum hardware and the particular noise channel, making it a versatile tool for quantum simulation. Applying quantum many-body machine learning techniques to error mitigation, our method is a promising strategy for extending the reach of near-term quantum computers to solve complex quantum simulation problems.

Deep regression for uncertainty-aware and interpretable analysis of large-scale body MRI arxiv:2105.07797 📈 3

Taro Langner, Robin Strand, Håkan Ahlström, Joel Kullberg

**Abstract:** Large-scale medical studies such as the UK Biobank examine thousands of volunteer participants with medical imaging techniques. Combined with the vast amount of collected metadata, anatomical information from these images has the potential for medical analyses at unprecedented scale. However, their evaluation often requires manual input and long processing times, limiting the amount of reference values for biomarkers and other measurements available for research. Recent approaches with convolutional neural networks for regression can perform these evaluations automatically. On magnetic resonance imaging (MRI) data of more than 40,000 UK Biobank subjects, these systems can estimate human age, body composition and more. This style of analysis is almost entirely data-driven and no manual intervention or guidance with manually segmented ground truth images is required. The networks often closely emulate the reference method that provided their training data and can reach levels of agreement comparable to the expected variability between established medical gold standard techniques. The risk of silent failure can be individually quantified by predictive uncertainty obtained from a mean-variance criterion and ensembling. Saliency analysis furthermore enables an interpretation of the underlying relevant image features and showed that the networks learned to correctly target specific organs, limbs, and regions of interest.

A Cloud-based Deep Learning Framework for Remote Detection of Diabetic Foot Ulcers arxiv:2105.07763 📈 3

Bill Cassidy, Neil D. Reeves, Joseph M. Pappachan, Naseer Ahmad, Samantha Haycocks, David Gillespie, Moi Hoon Yap

**Abstract:** This research proposes a mobile and cloud-based framework for the automatic detection of diabetic foot ulcers and conducts an investigation of its performance. The system uses a cross-platform mobile framework which enables the deployment of mobile apps to multiple platforms using a single TypeScript code base. A deep convolutional neural network was deployed to a cloud-based platform where the mobile app could send photographs of patient's feet for inference to detect the presence of diabetic foot ulcers. The functionality and usability of the system were tested in two clinical settings: Salford Royal NHS Foundation Trust and Lancashire Teaching Hospitals NHS Foundation Trust. The benefits of the system, such as the potential use of the app by patients to identify and monitor their condition are discussed.

Automated Biodesign Engineering by Abductive Meta-Interpretive Learning arxiv:2105.07758 📈 3

Wang-Zhou Dai, Liam Hallett, Stephen H. Muggleton, Geoff S. Baldwin

**Abstract:** The application of Artificial Intelligence (AI) to synthetic biology will provide the foundation for the creation of a high throughput automated platform for genetic design, in which a learning machine is used to iteratively optimise the system through a design-build-test-learn (DBTL) cycle. However, mainstream machine learning techniques represented by deep learning lacks the capability to represent relational knowledge and requires prodigious amounts of annotated training data. These drawbacks strongly restrict AI's role in synthetic biology in which experimentation is inherently resource and time intensive. In this work, we propose an automated biodesign engineering framework empowered by Abductive Meta-Interpretive Learning ($Meta_{Abd}$), a novel machine learning approach that combines symbolic and sub-symbolic machine learning, to further enhance the DBTL cycle by enabling the learning machine to 1) exploit domain knowledge and learn human-interpretable models that are expressed by formal languages such as first-order logic; 2) simultaneously optimise the structure and parameters of the models to make accurate numerical predictions; 3) reduce the cost of experiments and effort on data annotation by actively generating hypotheses and examples. To verify the effectiveness of $Meta_{Abd}$, we have modelled a synthetic dataset for the production of proteins from a three gene operon in a microbial host, which represents a common synthetic biology problem.

Universal Regular Conditional Distributions arxiv:2105.07743 📈 3

Anastasis Kratsios

**Abstract:** We introduce a general framework for approximating regular conditional distributions (RCDs). Our approximations of these RCDs are implemented by a new class of geometric deep learning models with inputs in $\mathbb{R}^d$ and outputs in the Wasserstein-$1$ space $\mathcal{P}_1(\mathbb{R}^D)$. We find that the models built using our framework can approximate any continuous functions from $\mathbb{R}^d$ to $\mathcal{P}_1(\mathbb{R}^D)$ uniformly on compacts, and quantitative rates are obtained. We identify two methods for avoiding the "curse of dimensionality"; i.e.: the number of parameters determining the approximating neural network depends only polynomially on the involved dimension and the approximation error. The first solution describes functions in $C(\mathbb{R}^d,\mathcal{P}_1(\mathbb{R}^D))$ which can be efficiently approximated on any compact subset of $\mathbb{R}^d$. Conversely, the second approach describes sets in $\mathbb{R}^d$, on which any function in $C(\mathbb{R}^d,\mathcal{P}_1(\mathbb{R}^D))$ can be efficiently approximated. Our framework is used to obtain an affirmative answer to the open conjecture of Bishop (1994); namely: mixture density networks are universal regular conditional distributions. The predictive performance of the proposed models is evaluated against comparable learning models on various probabilistic predictions tasks in the context of ELMs, model uncertainty, and heteroscedastic regression. All the results are obtained for more general input and output spaces and thus apply to geometric deep learning contexts.

The State of Infodemic on Twitter arxiv:2105.07730 📈 3

Drishti Jain, Tavpritesh Sethi

**Abstract:** Following the wave of misinterpreted, manipulated and malicious information growing on the Internet, the misinformation surrounding COVID-19 has become a paramount issue. In the context of the current COVID-19 pandemic, social media posts and platforms are at risk of rumors and misinformation in the face of the serious uncertainty surrounding the virus itself. At the same time, the uncertainty and new nature of COVID-19 means that other unconfirmed information that may appear "rumored" may be an important indicator of the behavior and impact of this new virus. Twitter, in particular, has taken a center stage in this storm where Covid-19 has been a much talked about subject. We have presented an exploratory analysis of the tweets and the users who are involved in spreading misinformation and then delved into machine learning models and natural language processing techniques to identify if a tweet contains misinformation.

Dependency Parsing as MRC-based Span-Span Prediction arxiv:2105.07654 📈 3

Leilei Gan, Yuxian Meng, Kun Kuang, Xiaofei Sun, Chun Fan, Fei Wu, Jiwei Li

**Abstract:** Higher-order methods for dependency parsing can partially but not fully addresses the issue that edges in dependency tree should be constructed at the text span/subtree level rather than word level. % This shortcoming can cause an incorrect span covered the corresponding tree rooted at a certain word though the word is correctly linked to its head. In this paper, we propose a new method for dependency parsing to address this issue. The proposed method constructs dependency trees by directly modeling span-span (in other words, subtree-subtree) relations. It consists of two modules: the {\it text span proposal module} which proposes candidate text spans, each of which represents a subtree in the dependency tree denoted by (root, start, end); and the {\it span linking module}, which constructs links between proposed spans. We use the machine reading comprehension (MRC) framework as the backbone to formalize the span linking module in an MRC setup, where one span is used as a query to extract the text span/subtree it should be linked to. The proposed method comes with the following merits: (1) it addresses the fundamental problem that edges in a dependency tree should be constructed between subtrees; (2) the MRC framework allows the method to retrieve missing spans in the span proposal stage, which leads to higher recall for eligible spans. Extensive experiments on the PTB, CTB and Universal Dependencies (UD) benchmarks demonstrate the effectiveness of the proposed method. We are able to achieve new SOTA performances on PTB and UD benchmarks, and competitive performances to previous SOTA models on the CTB dataset. Code is available at https://github.com/ShannonAI/mrc-for-dependency-parsing.

Shared and Private VAEs with Generative Replay for Continual Learning arxiv:2105.07627 📈 3

Subhankar Ghosh

**Abstract:** Continual learning tries to learn new tasks without forgetting previously learned ones. In reality, most of the existing artificial neural network(ANN) models fail, while humans do the same by remembering previous works throughout their life. Although simply storing all past data can alleviate the problem, it needs large memory and often infeasible in real-world applications where last data access is limited. We hypothesize that the model that learns to solve each task continually has some task-specific properties and some task-invariant characteristics. We propose a hybrid continual learning model that is more suitable in real case scenarios to address the issues that has a task-invariant shared variational autoencoder and T task-specific variational autoencoders. Our model combines generative replay and architectural growth to prevent catastrophic forgetting. We show our hybrid model effectively avoids forgetting and achieves state-of-the-art results on visual continual learning benchmarks such as MNIST, Permuted MNIST(QMNIST), CIFAR100, and miniImageNet datasets. We discuss results on a few more datasets, such as SVHN, Fashion-MNIST, EMNIST, and CIFAR10.

SemSegLoss: A python package of loss functions for semantic segmentation arxiv:2106.05844 📈 2

Shruti Jadon

**Abstract:** Image Segmentation has been an active field of research as it has a wide range of applications, ranging from automated disease detection to self-driving cars. In recent years, various research papers proposed different loss functions used in case of biased data, sparse segmentation, and unbalanced dataset. In this paper, we introduce SemSegLoss, a python package consisting of some of the well-known loss functions widely used for image segmentation. It is developed with the intent to help researchers in the development of novel loss functions and perform an extensive set of experiments on model architectures for various applications. The ease-of-use and flexibility of the presented package have allowed reducing the development time and increased evaluation strategies of machine learning models for semantic segmentation. Furthermore, different applications that use image segmentation can use SemSegLoss because of the generality of its functions. This wide range of applications will lead to the development and growth of AI across all industries.

Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report arxiv:2105.08630 📈 2

Andrey Ignatov, Grigory Malivenko, David Plowman, Samarth Shukla, Radu Timofte, Ziyu Zhang, Yicheng Wang, Zilong Huang, Guozhong Luo, Gang Yu, Bin Fu, Yiran Wang, Xingyi Li, Min Shi, Ke Xian, Zhiguo Cao, Jin-Hua Du, Pei-Lin Wu, Chao Ge, Jiaoyang Yao, Fangwen Tu, Bo Li, Jung Eun Yoo, Kwanggyoon Seo, Jialei Xu

**Abstract:** Depth estimation is an important computer vision problem with many practical applications to mobile devices. While many solutions have been proposed for this task, they are usually very computationally expensive and thus are not applicable for on-device inference. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly real-time performance on smartphones and IoT platforms. For this, the participants were provided with a new large-scale dataset containing RGB-depth image pairs obtained with a dedicated stereo ZED camera producing high-resolution depth maps for objects located at up to 50 meters. The runtime of all models was evaluated on the popular Raspberry Pi 4 platform with a mobile ARM-based Broadcom chipset. The proposed solutions can generate VGA resolution depth maps at up to 10 FPS on the Raspberry Pi 4 while achieving high fidelity results, and are compatible with any Android or Linux-based mobile devices. A detailed description of all models developed in the challenge is provided in this paper.

Sparta: Spatially Attentive and Adversarially Robust Activation arxiv:2105.08269 📈 2

Qing Guo, Felix Juefei-Xu, Changqing Zhou, Yang Liu, Song Wang

**Abstract:** Adversarial training (AT) is one of the most effective ways for improving the robustness of deep convolution neural networks (CNNs). Just like common network training, the effectiveness of AT relies on the design of basic network components. In this paper, we conduct an in-depth study on the role of the basic ReLU activation component in AT for robust CNNs. We find that the spatially-shared and input-independent properties of ReLU activation make CNNs less robust to white-box adversarial attacks with either standard or adversarial training. To address this problem, we extend ReLU to a novel Sparta activation function (Spatially attentive and Adversarially Robust Activation), which enables CNNs to achieve both higher robustness, i.e., lower error rate on adversarial examples, and higher accuracy, i.e., lower error rate on clean examples, than the existing state-of-the-art (SOTA) activation functions. We further study the relationship between Sparta and the SOTA activation functions, providing more insights about the advantages of our method. With comprehensive experiments, we also find that the proposed method exhibits superior cross-CNN and cross-dataset transferability. For the former, the adversarially trained Sparta function for one CNN (e.g., ResNet-18) can be fixed and directly used to train another adversarially robust CNN (e.g., ResNet-34). For the latter, the Sparta function trained on one dataset (e.g., CIFAR-10) can be employed to train adversarially robust CNNs on another dataset (e.g., SVHN). In both cases, Sparta leads to CNNs with higher robustness than the vanilla ReLU, verifying the flexibility and versatility of the proposed method.

Oneshot Differentially Private Top-k Selection arxiv:2105.08233 📈 2

Gang Qiao, Weijie J. Su, Li Zhang

**Abstract:** Being able to efficiently and accurately select the top-$k$ elements with differential privacy is an integral component of various private data analysis tasks. In this paper, we present the oneshot Laplace mechanism, which generalizes the well-known Report Noisy Max mechanism to reporting noisy top-$k$ elements. We show that the oneshot Laplace mechanism with a noise level of $\widetilde{O}(\sqrt{k}/\eps)$ is approximately differentially private. Compared to the previous peeling approach of running Report Noisy Max $k$ times, the oneshot Laplace mechanism only adds noises and computes the top $k$ elements once, hence much more efficient for large $k$. In addition, our proof of privacy relies on a novel coupling technique that bypasses the use of composition theorems. Finally, we present a novel application of efficient top-$k$ selection in the classical problem of ranking from pairwise comparisons.

Sharp Restricted Isometry Property Bounds for Low-rank Matrix Recovery Problems with Corrupted Measurements arxiv:2105.08232 📈 2

Ziye Ma, Yingjie Bi, Javad Lavaei, Somayeh Sojoudi

**Abstract:** In this paper, we study a general low-rank matrix recovery problem with linear measurements corrupted by some noise. The objective is to understand under what conditions on the restricted isometry property (RIP) of the problem local search methods can find the ground truth with a small error. By analyzing the landscape of the non-convex problem, we first propose a global guarantee on the maximum distance between an arbitrary local minimizer and the ground truth under the assumption that the RIP constant is smaller than $1/2$. We show that this distance shrinks to zero as the intensity of the noise reduces. Our new guarantee is sharp in terms of the RIP constant and is much stronger than the existing results. We then present a local guarantee for problems with an arbitrary RIP constant, which states that any local minimizer is either considerably close to the ground truth or far away from it. Next, we prove the strict saddle property, which guarantees the global convergence of the perturbed gradient descent method in polynomial time. The developed results demonstrate how the noise intensity and the RIP constant of the problem affect the landscape of the problem.

Reinforcement Learning for Adaptive Video Compressive Sensing arxiv:2105.08205 📈 2

Sidi Lu, Xin Yuan, Aggelos K Katsaggelos, Weisong Shi

**Abstract:** We apply reinforcement learning to video compressive sensing to adapt the compression ratio. Specifically, video snapshot compressive imaging (SCI), which captures high-speed video using a low-speed camera is considered in this work, in which multiple (B) video frames can be reconstructed from a snapshot measurement. One research gap in previous studies is how to adapt B in the video SCI system for different scenes. In this paper, we fill this gap utilizing reinforcement learning (RL). An RL model, as well as various convolutional neural networks for reconstruction, are learned to achieve adaptive sensing of video SCI systems. Furthermore, the performance of an object detection network using directly the video SCI measurements without reconstruction is also used to perform RL-based adaptive video compressive sensing. Our proposed adaptive SCI method can thus be implemented in low cost and real time. Our work takes the technology one step further towards real applications of video SCI.

Randomly Initialized Convolutional Neural Network for the Recognition of COVID-19 using X-ray Images arxiv:2105.08199 📈 2

Safa Ben Atitallah, Maha Driss, Wadii Boulila, Henda Ben Ghézala

**Abstract:** By the start of 2020, the novel coronavirus disease (COVID-19) has been declared a worldwide pandemic. Because of the severity of this infectious disease, several kinds of research have focused on combatting its ongoing spread. One potential solution to detect COVID-19 is by analyzing the chest X-ray images using Deep Learning (DL) models. In this context, Convolutional Neural Networks (CNNs) are presented as efficient techniques for early diagnosis. In this study, we propose a novel randomly initialized CNN architecture for the recognition of COVID-19. This network consists of a set of different-sized hidden layers created from scratch. The performance of this network is evaluated through two public datasets, which are the COVIDx and the enhanced COVID-19 datasets. Both of these datasets consist of 3 different classes of images: COVID19, pneumonia, and normal chest X-ray images. The proposed CNN model yields encouraging results with 94% and 99% of accuracy for COVIDx and enhanced COVID-19 dataset, respectively.

Graph Neural Networks for Knowledge Enhanced Visual Representation of Paintings arxiv:2105.08190 📈 2

Athanasios Efthymiou, Stevan Rudinac, Monika Kackovic, Marcel Worring, Nachoem Wijnberg

**Abstract:** We propose ArtSAGENet, a novel multimodal architecture that integrates Graph Neural Networks (GNNs) and Convolutional Neural Networks (CNNs), to jointly learn visual and semantic-based artistic representations. First, we illustrate the significant advantages of multi-task learning for fine art analysis and argue that it is conceptually a much more appropriate setting in the fine art domain than the single-task alternatives. We further demonstrate that several GNN architectures can outperform strong CNN baselines in a range of fine art analysis tasks, such as style classification, artist attribution, creation period estimation, and tag prediction, while training them requires an order of magnitude less computational time and only a small amount of labeled data. Finally, through extensive experimentation we show that our proposed ArtSAGENet captures and encodes valuable relational dependencies between the artists and the artworks, surpassing the performance of traditional methods that rely solely on the analysis of visual content. Our findings underline a great potential of integrating visual content and semantics for fine art analysis and curation.

Modeling the EdNet Dataset with Logistic Regression arxiv:2105.08150 📈 2

Philip I. Pavlik Jr, Luke G. Eglington

**Abstract:** Many of these challenges are won by neural network models created by full-time artificial intelligence scientists. Due to this origin, they have a black-box character that makes their use and application less clear to learning scientists. We describe our experience with competition from the perspective of educational data mining, a field founded in the learning sciences and connected with roots in psychology and statistics. We describe our efforts from the perspectives of learning scientists and the challenges to our methods, some real and some imagined. We also discuss some basic results in the Kaggle system and our thoughts on how those results may have been improved. Finally, we describe how learner model predictions are used to make pedagogical decisions for students. Their practical use entails a) model predictions and b) a decision rule (based on the predictions). We point out how increased model accuracy can be of limited practical utility, especially when paired with simple decision rules and argue instead for the need to further investigate optimal decision rules.

Deep Metric Learning for Few-Shot Image Classification: A Selective Review arxiv:2105.08149 📈 2

Xiaoxu Li, Xiaochen Yang, Zhanyu Ma, Jing-Hao Xue

**Abstract:** Few-shot image classification is a challenging problem which aims to achieve the human level of recognition based only on a small number of images. Deep learning algorithms such as meta-learning, transfer learning, and metric learning have been employed recently and achieved the state-of-the-art performance. In this survey, we review representative deep metric learning methods for few-shot classification, and categorize them into three groups according to the major problems and novelties they focus on. We conclude this review with a discussion on current challenges and future trends in few-shot image classification.

Automatic Fault Detection for Deep Learning Programs Using Graph Transformations arxiv:2105.08095 📈 2

Amin Nikanjam, Houssem Ben Braiek, Mohammad Mehdi Morovati, Foutse Khomh

**Abstract:** Nowadays, we are witnessing an increasing demand in both corporates and academia for exploiting Deep Learning (DL) to solve complex real-world problems. A DL program encodes the network structure of a desirable DL model and the process by which the model learns from the training dataset. Like any software, a DL program can be faulty, which implies substantial challenges of software quality assurance, especially in safety-critical domains. It is therefore crucial to equip DL development teams with efficient fault detection techniques and tools. In this paper, we propose NeuraLint, a model-based fault detection approach for DL programs, using meta-modelling and graph transformations. First, we design a meta-model for DL programs that includes their base skeleton and fundamental properties. Then, we construct a graph-based verification process that covers 23 rules defined on top of the meta-model and implemented as graph transformations to detect faults and design inefficiencies in the generated models (i.e., instances of the meta-model). First, the proposed approach is evaluated by finding faults and design inefficiencies in 28 synthesized examples built from common problems reported in the literature. Then NeuraLint successfully finds 64 faults and design inefficiencies in 34 real-world DL programs extracted from Stack Overflow posts and GitHub repositories. The results show that NeuraLint effectively detects faults and design issues in both synthesized and real-world examples with a recall of 70.5 % and a precision of 100 %. Although the proposed meta-model is designed for feedforward neural networks, it can be extended to support other neural network architectures such as recurrent neural networks. Researchers can also expand our set of verification rules to cover more types of issues in DL programs.

A Review on Explainability in Multimodal Deep Neural Nets arxiv:2105.07878 📈 2

Gargi Joshi, Rahee Walambe, Ketan Kotecha

**Abstract:** Artificial Intelligence techniques powered by deep neural nets have achieved much success in several application domains, most significantly and notably in the Computer Vision applications and Natural Language Processing tasks. Surpassing human-level performance propelled the research in the applications where different modalities amongst language, vision, sensory, text play an important role in accurate predictions and identification. Several multimodal fusion methods employing deep learning models are proposed in the literature. Despite their outstanding performance, the complex, opaque and black-box nature of the deep neural nets limits their social acceptance and usability. This has given rise to the quest for model interpretability and explainability, more so in the complex tasks involving multimodal AI methods. This paper extensively reviews the present literature to present a comprehensive survey and commentary on the explainability in multimodal deep neural nets, especially for the vision and language tasks. Several topics on multimodal AI and its applications for generic domains have been covered in this paper, including the significance, datasets, fundamental building blocks of the methods and techniques, challenges, applications, and future trends in this domain

Deep Learning Models in Software Requirements Engineering arxiv:2105.07771 📈 2

Maria Naumcheva

**Abstract:** Requirements elicitation is an important phase of any software project: the errors in requirements are more expensive to fix than the errors introduced at later stages of software life cycle. Nevertheless, many projects do not devote sufficient time to requirements. Automated requirements generation can improve the quality of software projects. In this article we have accomplished the first step of the research on this topic: we have applied the vanilla sentence autoencoder to the sentence generation task and evaluated its performance. The generated sentences are not plausible English and contain only a few meaningful words. We believe that applying the model to a larger dataset may produce significantly better results. Further research is needed to improve the quality of generated data.

A Fusion-Denoising Attack on InstaHide with Data Augmentation arxiv:2105.07754 📈 2

Xinjian Luo, Xiaokui Xiao, Yuncheng Wu, Juncheng Liu, Beng Chin Ooi

**Abstract:** InstaHide is a state-of-the-art mechanism for protecting private training images, by mixing multiple private images and modifying them such that their visual features are indistinguishable to the naked eye. In recent work, however, Carlini et al. show that it is possible to reconstruct private images from the encrypted dataset generated by InstaHide. Nevertheless, we demonstrate that Carlini et al.'s attack can be easily defeated by incorporating data augmentation into InstaHide. This leads to a natural question: is InstaHide with data augmentation secure? In this paper, we provide a negative answer to this question, by devising an attack for recovering private images from the outputs of InstaHide even when data augmentation is present. The basic idea is to use a comparative network to identify encrypted images that are likely to correspond to the same private image, and then employ a fusion-denoising network for restoring the private image from the encrypted ones, taking into account the effects of data augmentation. Extensive experiments demonstrate the effectiveness of the proposed attack in comparison to Carlini et al.'s attack.

Generic Itemset Mining Based on Reinforcement Learning arxiv:2105.07753 📈 2

Kazuma Fujioka, Kimiaki Shirahama

**Abstract:** One of the biggest problems in itemset mining is the requirement of developing a data structure or algorithm, every time a user wants to extract a different type of itemsets. To overcome this, we propose a method, called Generic Itemset Mining based on Reinforcement Learning (GIM-RL), that offers a unified framework to train an agent for extracting any type of itemsets. In GIM-RL, the environment formulates iterative steps of extracting a target type of itemsets from a dataset. At each step, an agent performs an action to add or remove an item to or from the current itemset, and then obtains from the environment a reward that represents how relevant the itemset resulting from the action is to the target type. Through numerous trial-and-error steps where various rewards are obtained by diverse actions, the agent is trained to maximise cumulative rewards so that it acquires the optimal action policy for forming as many itemsets of the target type as possible. In this framework, an agent for extracting any type of itemsets can be trained as long as a reward suitable for the type can be defined. The extensive experiments on mining high utility itemsets, frequent itemsets and association rules show the general effectiveness and one remarkable potential (agent transfer) of GIM-RL. We hope that GIM-RL opens a new research direction towards learning-based itemset mining.

ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale arxiv:2105.08275 📈 1

Yuanming Li, Huaizheng Zhang, Shanshan Jiang, Fan Yang, Yonggang Wen, Yong Luo

**Abstract:** AI engineering has emerged as a crucial discipline to democratize deep neural network (DNN) models among software developers with a diverse background. In particular, altering these DNN models in the deployment stage posits a tremendous challenge. In this research, we propose and develop a low-code solution, ModelPS (an acronym for "Model Photoshop"), to enable and empower collaborative DNN model editing and intelligent model serving. The ModelPS solution embodies two transformative features: 1) a user-friendly web interface for a developer team to share and edit DNN models pictorially, in a low-code fashion, and 2) a model genie engine in the backend to aid developers in customizing model editing configurations for given deployment requirements or constraints. Our case studies with a wide range of deep learning (DL) models show that the system can tremendously reduce both development and communication overheads with improved productivity.

EchoCP: An Echocardiography Dataset in Contrast Transthoracic Echocardiography for Patent Foramen Ovale Diagnosis arxiv:2105.08267 📈 1

Tianchen Wang, Zhihe Li, Meiping Huang, Jian Zhuang, Shanshan Bi, Jiawei Zhang, Yiyu Shi, Hongwen Fei, Xiaowei Xu

**Abstract:** Patent foramen ovale (PFO) is a potential separation between the septum, primum and septum secundum located in the anterosuperior portion of the atrial septum. PFO is one of the main factors causing cryptogenic stroke which is the fifth leading cause of death in the United States. For PFO diagnosis, contrast transthoracic echocardiography (cTTE) is preferred as being a more robust method compared with others. However, the current PFO diagnosis through cTTE is extremely slow as it is proceeded manually by sonographers on echocardiography videos. Currently there is no publicly available dataset for this important topic in the community. In this paper, we present EchoCP, as the first echocardiography dataset in cTTE targeting PFO diagnosis. EchoCP consists of 30 patients with both rest and Valsalva maneuver videos which covers various PFO grades. We further establish an automated baseline method for PFO diagnosis based on the state-of-the-art cardiac chamber segmentation technique, which achieves 0.89 average mean Dice score, but only 0.60/0.67 mean accuracies for PFO diagnosis, leaving large room for improvement. We hope that the challenging EchoCP dataset can stimulate further research and lead to innovative and generic solutions that would have an impact in multiple domains. Our dataset is released.

Arrested phase separation in double-exchange models: machine-learning enabled large-scale simulation arxiv:2105.08221 📈 1

Puhan Zhang, Gia-Wei Chern

**Abstract:** We present large-scale dynamical simulations of electronic phase separation in the single-band double-exchange model based on deep-learning neural-network potentials trained from small-size exact diagonalization solutions. We uncover an intriguing correlation-induced freezing behavior as doped holes are segregated from half-filled insulating background during equilibration. While the aggregation of holes is stabilized by the formation of ferromagnetic clusters through Hund's coupling between charge carriers and local magnetic moments, this stabilization also creates confining potentials for holes when antiferromagnetic spin-spin correlation is well developed in the background. The dramatically reduced mobility of the self-trapped holes prematurely disrupts further growth of the ferromagnetic clusters, leading to an arrested phase separation. Implications of our findings for phase separation dynamics in materials that exhibit colossal magnetoresistance effect are discussed.

Accelerating 3D MULTIPLEX MRI Reconstruction with Deep Learning arxiv:2105.08163 📈 1

Eric Z. Chen, Yongquan Ye, Xiao Chen, Jingyuan Lyu, Zhongqi Zhang, Yichen Hu, Terrence Chen, Jian Xu, Shanhui Sun

**Abstract:** Multi-contrast MRI images provide complementary contrast information about the characteristics of anatomical structures and are commonly used in clinical practice. Recently, a multi-flip-angle (FA) and multi-echo GRE method (MULTIPLEX MRI) has been developed to simultaneously acquire multiple parametric images with just one single scan. However, it poses two challenges for MULTIPLEX to be used in the 3D high-resolution setting: a relatively long scan time and the huge amount of 3D multi-contrast data for reconstruction. Currently, no DL based method has been proposed for 3D MULTIPLEX data reconstruction. We propose a deep learning framework for undersampled 3D MRI data reconstruction and apply it to MULTIPLEX MRI. The proposed deep learning method shows good performance in image quality and reconstruction time.

Livewired Neural Networks: Making Neurons That Fire Together Wire Together arxiv:2105.08111 📈 1

Thomas Schumacher

**Abstract:** Until recently, artificial neural networks were typically designed with a fixed network structure. Here, I argue that network structure is highly relevant to function, and therefore neural networks should be livewired (Eagleman 2020): dynamically rewired to reflect relationships between higher order representations of the external environment identified by coincident activations in individual neurons. I discuss how this approach may enable such networks to build compositional world models that operate on symbols and that achieve few-shot learning, capabilities thought by many to be critical to human-level cognition. Here, I also 1) discuss how such livewired neural networks maximize the information the environment provides to a model, 2) explore evidence indicating that livewiring is implemented in the brain, guided by glial cells, 3) discuss how livewiring may give rise to the associative emergent behaviors of brains, and 4) suggest paths for future research using livewired networks to understand and create human-like reasoning.

DFENet: A Novel Dimension Fusion Edge Guided Network for Brain MRI Segmentation arxiv:2105.07962 📈 1

Hritam Basak, Rukhshanda Hussain, Ajay Rana

**Abstract:** The rapid increment of morbidity of brain stroke in the last few years have been a driving force towards fast and accurate segmentation of stroke lesions from brain MRI images. With the recent development of deep-learning, computer-aided and segmentation methods of ischemic stroke lesions have been useful for clinicians in early diagnosis and treatment planning. However, most of these methods suffer from inaccurate and unreliable segmentation results because of their inability to capture sufficient contextual features from the MRI volumes. To meet these requirements, 3D convolutional neural networks have been proposed, which, however, suffer from huge computational requirements. To mitigate these problems, we propose a novel Dimension Fusion Edge-guided network (DFENet) that can meet both of these requirements by fusing the features of 2D and 3D CNNs. Unlike other methods, our proposed network uses a parallel partial decoder (PPD) module for aggregating and upsampling selected features, rich in important contextual information. Additionally, we use an edge-guidance and enhanced mixing loss for constantly supervising and improvising the learning process of the network. The proposed method is evaluated on publicly available Anatomical Tracings of Lesions After Stroke (ATLAS) dataset, resulting in mean DSC, IoU, Precision and Recall values of 0.5457, 0.4015, 0.6371, and 0.4969 respectively. The results, when compared to other state-of-the-art methods, outperforms them by a significant margin. Therefore, the proposed model is robust, accurate, superior to the existing methods, and can be relied upon for biomedical applications.

Joint Optimization of Hadamard Sensing and Reconstruction in Compressed Sensing Fluorescence Microscopy arxiv:2105.07961 📈 1

Alan Q. Wang, Aaron K. LaViolette, Leo Moon, Chris Xu, Mert R. Sabuncu

**Abstract:** Compressed sensing fluorescence microscopy (CS-FM) proposes a scheme whereby less measurements are collected during sensing and reconstruction is performed to recover the image. Much work has gone into optimizing the sensing and reconstruction portions separately. We propose a method of jointly optimizing both sensing and reconstruction end-to-end under a total measurement constraint, enabling learning of the optimal sensing scheme concurrently with the parameters of a neural network-based reconstruction network. We train our model on a rich dataset of confocal, two-photon, and wide-field microscopy images comprising of a variety of biological samples. We show that our method outperforms several baseline sensing schemes and a regularized regression reconstruction algorithm.

Behavior-based Neuroevolutionary Training in Reinforcement Learning arxiv:2105.07960 📈 1

Jörg Stork, Martin Zaefferer, Nils Eisler, Patrick Tichelmann, Thomas Bartz-Beielstein, A. E. Eiben

**Abstract:** In addition to their undisputed success in solving classical optimization problems, neuroevolutionary and population-based algorithms have become an alternative to standard reinforcement learning methods. However, evolutionary methods often lack the sample efficiency of standard value-based methods that leverage gathered state and value experience. If reinforcement learning for real-world problems with significant resource cost is considered, sample efficiency is essential. The enhancement of evolutionary algorithms with experience exploiting methods is thus desired and promises valuable insights. This work presents a hybrid algorithm that combines topology-changing neuroevolutionary optimization with value-based reinforcement learning. We illustrate how the behavior of policies can be used to create distance and loss functions, which benefit from stored experiences and calculated state values. They allow us to model behavior and perform a directed search in the behavior space by gradient-free evolutionary algorithms and surrogate-based optimization. For this purpose, we consolidate different methods to generate and optimize agent policies, creating a diverse population. We exemplify the performance of our algorithm on standard benchmarks and a purpose-built real-world problem. Our results indicate that combining methods can enhance the sample efficiency and learning speed for evolutionary approaches.

DISCO Verification: Division of Input Space into COnvex polytopes for neural network verification arxiv:2105.07776 📈 1

Julien Girard-Satabin, Aymeric Varasse, Marc Schoenauer, Guillaume Charpiat, Zakaria Chihani

**Abstract:** The impressive results of modern neural networks partly come from their non linear behaviour. Unfortunately, this property makes it very difficult to apply formal verification tools, even if we restrict ourselves to networks with a piecewise linear structure. However, such networks yields subregions that are linear and thus simpler to analyse independently. In this paper, we propose a method to simplify the verification problem by operating a partitionning into multiple linear subproblems. To evaluate the feasibility of such an approach, we perform an empirical analysis of neural networks to estimate the number of linear regions, and compare them to the bounds currently known. We also present the impact of a technique aiming at reducing the number of linear regions during training.

Data Assimilation Predictive GAN (DA-PredGAN): applied to determine the spread of COVID-19 arxiv:2105.07729 📈 1

Vinicius L. S. Silva, Claire E. Heaney, Yaqi Li, Christopher C. Pain

**Abstract:** We propose the novel use of a generative adversarial network (GAN) (i) to make predictions in time (PredGAN) and (ii) to assimilate measurements (DA-PredGAN). In the latter case, we take advantage of the natural adjoint-like properties of generative models and the ability to simulate forwards and backwards in time. GANs have received much attention recently, after achieving excellent results for their generation of realistic-looking images. We wish to explore how this property translates to new applications in computational modelling and to exploit the adjoint-like properties for efficient data assimilation. To predict the spread of COVID-19 in an idealised town, we apply these methods to a compartmental model in epidemiology that is able to model space and time variations. To do this, the GAN is set within a reduced-order model (ROM), which uses a low-dimensional space for the spatial distribution of the simulation states. Then the GAN learns the evolution of the low-dimensional states over time. The results show that the proposed methods can accurately predict the evolution of the high-fidelity numerical simulation, and can efficiently assimilate observed data and determine the corresponding model parameters.

Probabilistic robust linear quadratic regulators with Gaussian processes arxiv:2105.07668 📈 1

Alexander von Rohr, Matthias Neumann-Brosig, Sebastian Trimpe

**Abstract:** Probabilistic models such as Gaussian processes (GPs) are powerful tools to learn unknown dynamical systems from data for subsequent use in control design. While learning-based control has the potential to yield superior performance in demanding applications, robustness to uncertainty remains an important challenge. Since Bayesian methods quantify uncertainty of the learning results, it is natural to incorporate these uncertainties into a robust design. In contrast to most state-of-the-art approaches that consider worst-case estimates, we leverage the learning method's posterior distribution in the controller synthesis. The result is a more informed and, thus, more efficient trade-off between performance and robustness. We present a novel controller synthesis for linearized GP dynamics that yields robust controllers with respect to a probabilistic stability margin. The formulation is based on a recently proposed algorithm for linear quadratic control synthesis, which we extend by giving probabilistic robustness guarantees in the form of credibility bounds for the system's stability.Comparisons to existing methods based on worst-case and certainty-equivalence designs reveal superior performance and robustness properties of the proposed method.

Comparison of machine learning and deep learning techniques in promoter prediction across diverse species arxiv:2105.07659 📈 1

Nikita Bhandari, Satyajeet Khare, Rahee Walambe, Ketan Kotecha

**Abstract:** Gene promoters are the key DNA regulatory elements positioned around the transcription start sites and are responsible for regulating gene transcription process. Various alignment-based, signal-based and content-based approaches are reported for the prediction of promoters. However, since all promoter sequences do not show explicit features, the prediction performance of these techniques is poor. Therefore, many machine learning and deep learning models have been proposed for promoter prediction. In this work, we studied methods for vector encoding and promoter classification using genome sequences of three distinct higher eukaryotes viz. yeast (Saccharomyces cerevisiae), A. thaliana (plant) and human (Homo sapiens). We compared one-hot vector encoding method with frequency-based tokenization (FBT) for data pre-processing on 1-D Convolutional Neural Network (CNN) model. We found that FBT gives a shorter input dimension reducing the training time without affecting the sensitivity and specificity of classification. We employed the deep learning techniques, mainly CNN and recurrent neural network with Long Short Term Memory (LSTM) and random forest (RF) classifier for promoter classification at k-mer sizes of 2, 4 and 8. We found CNN to be superior in classification of promoters from non-promoter sequences (binary classification) as well as species-specific classification of promoter sequences (multiclass classification). In summary, the contribution of this work lies in the use of synthetic shuffled negative dataset and frequency-based tokenization for pre-processing. This study provides a comprehensive and generic framework for classification tasks in genomic applications and can be extended to various classification problems.

Traffic-Aware Service Relocation in Cloud-Oriented Elastic Optical Networks arxiv:2105.07653 📈 1

Róża Goścień

**Abstract:** In this paper, we study problem of efficient service relocation (i.e., changing assigned data center for a selected client node) in elastic optical networks (EONs) in order to increase network performance (measured by the volume of accepted traffic). To this end, we first propose novel traffic model for cloud ready transport networks. The model takes into account four flow types (i.e., city-to-city, city-to-data center, data center-to-data center and data center-to-data center) while the flow characteristics are based on real economical and geographical parameters of the cities related to network nodes. Then, we propose dedicated flow allocation algorithm that can be supported by the service relocation process. We also introduce 21 different relocation policies, which use three types of data for decision making - network topological characteristics, rejection history and traffic prediction. Eventually, we perform extensive numerical experiments in order to: (i) tune proposed optimization approaches and (ii) evaluate and compare their efficiency and select the best one. The results of the investigation prove high efficiency of the proposed policies. The propoerly designed relocation policy allowed to allocate up to 3% more traffic (compared to the allocation without that policy). The results also reveal that the most efficient relocation policy bases its decisions on two types of data simultaneously - the rejection history and traffic prediction.

Learning Disentangled Representations for Time Series arxiv:2105.08179 📈 0

Yuening Li, Zhengzhang Chen, Daochen Zha, Mengnan Du, Denghui Zhang, Haifeng Chen, Xia Hu

**Abstract:** Time-series representation learning is a fundamental task for time-series analysis. While significant progress has been made to achieve accurate representations for downstream applications, the learned representations often lack interpretability and do not expose semantic meanings. Different from previous efforts on the entangled feature space, we aim to extract the semantic-rich temporal correlations in the latent interpretable factorized representation of the data. Motivated by the success of disentangled representation learning in computer vision, we study the possibility of learning semantic-rich time-series representations, which remains unexplored due to three main challenges: 1) sequential data structure introduces complex temporal correlations and makes the latent representations hard to interpret, 2) sequential models suffer from KL vanishing problem, and 3) interpretable semantic concepts for time-series often rely on multiple factors instead of individuals. To bridge the gap, we propose Disentangle Time Series (DTS), a novel disentanglement enhancement framework for sequential data. Specifically, to generate hierarchical semantic concepts as the interpretable and disentangled representation of time-series, DTS introduces multi-level disentanglement strategies by covering both individual latent factors and group semantic segments. We further theoretically show how to alleviate the KL vanishing problem: DTS introduces a mutual information maximization term, while preserving a heavier penalty on the total correlation and the dimension-wise KL to keep the disentanglement property. Experimental results on various real-world benchmark datasets demonstrate that the representations learned by DTS achieve superior performance in downstream applications, with high interpretability of semantic concepts.

Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement arxiv:2105.08040 📈 0

Mehmet Akçakaya, Burhaneddin Yaman, Hyungjin Chung, Jong Chul Ye

**Abstract:** Recently, deep learning approaches have become the main research frontier for biological image reconstruction and enhancement problems thanks to their high performance, along with their ultra-fast inference times. However, due to the difficulty of obtaining matched reference data for supervised learning, there has been increasing interest in unsupervised learning approaches that do not need paired reference data. In particular, self-supervised learning and generative models have been successfully used for various biological imaging applications. In this paper, we overview these approaches from a coherent perspective in the context of classical inverse problems, and discuss their applications to biological imaging, including electron, fluorescence and deconvolution microscopy, optical diffraction tomography and functional neuroimaging.

How to Explain Neural Networks: an Approximation Perspective arxiv:2105.07831 📈 0

Hangcheng Dong, Bingguo Liu, Fengdong Chen, Dong Ye, Guodong Liu

**Abstract:** The lack of interpretability has hindered the large-scale adoption of AI technologies. However, the fundamental idea of interpretability, as well as how to put it into practice, remains unclear. We provide notions of interpretability based on approximation theory in this study. We first implement this approximation interpretation on a specific model (fully connected neural network) and then propose to use MLP as a universal interpreter to explain arbitrary black-box models. Extensive experiments demonstrate the effectiveness of our approach.

Convex optimization for actionable \& plausible counterfactual explanations arxiv:2105.07630 📈 0

André Artelt, Barbara Hammer

**Abstract:** Transparency is an essential requirement of machine learning based decision making systems that are deployed in real world. Often, transparency of a given system is achieved by providing explanations of the behavior and predictions of the given system. Counterfactual explanations are a prominent instance of particular intuitive explanations of decision making systems. While a lot of different methods for computing counterfactual explanations exist, only very few work (apart from work from the causality domain) considers feature dependencies as well as plausibility which might limit the set of possible counterfactual explanations. In this work we enhance our previous work on convex modeling for computing counterfactual explanations by a mechanism for ensuring actionability and plausibility of the resulting counterfactual explanations.

Next Page