February 2, 2020

3348 words 16 mins read

Paper Group AWR 38

Explainable Knowledge Graph-based Recommendation via Deep Reinforcement Learning. Partially Encrypted Machine Learning using Functional Encryption. The Design and Implementation of a Real Time Visual Search System on JD E-commerce Platform. SaLite : A light-weight model for salient object detection. ntuer at SemEval-2019 Task 3: Emotion Classificat …

Explainable Knowledge Graph-based Recommendation via Deep Reinforcement Learning


Title	Explainable Knowledge Graph-based Recommendation via Deep Reinforcement Learning
Authors	Weiping Song, Zhijian Duan, Ziqing Yang, Hao Zhu, Ming Zhang, Jian Tang
Abstract	This paper studies recommender systems with knowledge graphs, which can effectively address the problems of data sparsity and cold start. Recently, a variety of methods have been developed for this problem, which generally try to learn effective representations of users and items and then match items to users according to their representations. Though these methods have been shown quite effective, they lack good explanations, which are critical to recommender systems. In this paper, we take a different path and propose generating recommendations by finding meaningful paths from users to items. Specifically, we formulate the problem as a sequential decision process, where the target user is defined as the initial state, and the walks on the graphs are defined as actions. We shape the rewards according to existing state-of-the-art methods and then train a policy function with policy gradient methods. Experimental results on three real-world datasets show that our proposed method not only provides effective recommendations but also offers good explanations.
Tasks	Knowledge Graphs, Policy Gradient Methods, Recommendation Systems
Published	2019-06-22
URL	https://arxiv.org/abs/1906.09506v1
PDF	https://arxiv.org/pdf/1906.09506v1.pdf
PWC	https://paperswithcode.com/paper/explainable-knowledge-graph-based
Repo	https://github.com/Pblamichha42/DynamicGAT
Framework	tf

Partially Encrypted Machine Learning using Functional Encryption


Title	Partially Encrypted Machine Learning using Functional Encryption
Authors	Theo Ryffel, Edouard Dufour-Sans, Romain Gay, Francis Bach, David Pointcheval
Abstract	Machine learning on encrypted data has received a lot of attention thanks to recent breakthroughs in homomorphic encryption and secure multi-party computation. It allows outsourcing computation to untrusted servers without sacrificing privacy of sensitive data. We propose a practical framework to perform partially encrypted and privacy-preserving predictions which combines adversarial training and functional encryption. We first present a new functional encryption scheme to efficiently compute quadratic functions so that the data owner controls what can be computed but is not involved in the calculation: it provides a decryption key which allows one to learn a specific function evaluation of some encrypted data. We then show how to use it in machine learning to partially encrypt neural networks with quadratic activation functions at evaluation time, and we provide a thorough analysis of the information leaks based on indistinguishability of data items of the same label. Last, since most encryption schemes cannot deal with the last thresholding operation used for classification, we propose a training method to prevent selected sensitive features from leaking, which adversarially optimizes the network against an adversary trying to identify these features. This is interesting for several existing works using partially encrypted machine learning as it comes with little reduction on the model’s accuracy and significantly improves data privacy.
Tasks
Published	2019-05-24
URL	https://arxiv.org/abs/1905.10214v4
PDF	https://arxiv.org/pdf/1905.10214v4.pdf
PWC	https://paperswithcode.com/paper/partially-encrypted-machine-learning-using
Repo	https://github.com/LaRiffle/collateral-learning
Framework	pytorch

The Design and Implementation of a Real Time Visual Search System on JD E-commerce Platform


Title	The Design and Implementation of a Real Time Visual Search System on JD E-commerce Platform
Authors	Jie Li, Haifeng Liu, Chuanghua Gui, Jianyu Chen, Zhenyun Ni, Ning Wang
Abstract	We present the design and implementation of a visual search system for real time image retrieval on JD.com, the world’s third largest and China’s largest e-commerce site. We demonstrate that our system can support real time visual search with hundreds of billions of product images at sub-second timescales and handle frequent image updates through distributed hierarchical architecture and efficient indexing methods. We hope that sharing our practice with our real production system will inspire the middleware community’s interest and appreciation for building practical large scale systems for emerging applications, such as ecommerce visual search.
Tasks	Image Retrieval
Published	2019-08-19
URL	https://arxiv.org/abs/1908.07389v1
PDF	https://arxiv.org/pdf/1908.07389v1.pdf
PWC	https://paperswithcode.com/paper/the-design-and-implementation-of-a-real-time
Repo	https://github.com/vearch/vearch
Framework	none

SaLite : A light-weight model for salient object detection


Title	SaLite : A light-weight model for salient object detection
Authors	Kitty Varghese, Sauradip Nag
Abstract	Salient object detection is a prevalent computer vision task that has applications ranging from abnormality detection to abnormality processing. Context modelling is an important criterion in the domain of saliency detection. A global context helps in determining the salient object in a given image by contrasting away other objects in the global view of the scene. However, the local context features detects the boundaries of the salient object with higher accuracy in a given region. To incorporate the best of both worlds, our proposed SaLite model uses both global and local contextual features. It is an encoder-decoder based architecture in which the encoder uses a lightweight SqueezeNet and decoder is modelled using convolution layers. Modern deep based models entitled for saliency detection use a large number of parameters, which is difficult to deploy on embedded systems. This paper attempts to solve the above problem using SaLite which is a lighter process for salient object detection without compromising on performance. Our approach is extensively evaluated on three publicly available datasets namely DUTS, MSRA10K, and SOC. Experimental results show that our proposed SaLite has significant and consistent improvements over the state-of-the-art methods.
Tasks	Anomaly Detection, Object Detection, Saliency Detection, Salient Object Detection
Published	2019-12-08
URL	https://arxiv.org/abs/1912.03641v1
PDF	https://arxiv.org/pdf/1912.03641v1.pdf
PWC	https://paperswithcode.com/paper/salite-a-light-weight-model-for-salient
Repo	https://github.com/kittyvarghese/lightweight_saliency_detection
Framework	pytorch

ntuer at SemEval-2019 Task 3: Emotion Classification with Word and Sentence Representations in RCNN


Title	ntuer at SemEval-2019 Task 3: Emotion Classification with Word and Sentence Representations in RCNN
Authors	Peixiang Zhong, Chunyan Miao
Abstract	In this paper we present our model on the task of emotion detection in textual conversations in SemEval-2019. Our model extends the Recurrent Convolutional Neural Network (RCNN) by using external fine-tuned word representations and DeepMoji sentence representations. We also explored several other competitive pre-trained word and sentence representations including ELMo, BERT and InferSent but found inferior performance. In addition, we conducted extensive sensitivity analysis, which empirically shows that our model is relatively robust to hyper-parameters. Our model requires no handcrafted features or emotion lexicons but achieved good performance with a micro-F1 score of 0.7463.
Tasks	Emotion Classification
Published	2019-02-21
URL	http://arxiv.org/abs/1902.07867v2
PDF	http://arxiv.org/pdf/1902.07867v2.pdf
PWC	https://paperswithcode.com/paper/ntuer-at-semeval-2019-task-3-emotion
Repo	https://github.com/zhongpeixiang/SemEval2019-Task3-EmotionDetection
Framework	pytorch

Options as responses: Grounding behavioural hierarchies in multi-agent RL


Title	Options as responses: Grounding behavioural hierarchies in multi-agent RL
Authors	Alexander Sasha Vezhnevets, Yuhuai Wu, Remi Leblond, Joel Z. Leibo
Abstract	We propose a novel hierarchical agent architecture for multi-agent reinforcement learning with concealed information. The hierarchy is grounded in the concealed information about other players, which resolves “the chicken or the egg” nature of option discovery. We factorise the value function over a latent representation of the concealed information and then re-use this latent space to factorise the policy into options. Low-level policies (options) are trained to respond to particular states of other agents grouped by the latent representation, while the top level (meta-policy) learns to infer the latent representation from its own observation thereby to select the right option. This grounding facilitates credit assignment across the levels of hierarchy. We show that this helps generalisation—performance against a held-out set of pre-trained competitors, while training in self- or population-play—and resolution of social dilemmas in self-play.
Tasks	Multi-agent Reinforcement Learning
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01470v2
PDF	https://arxiv.org/pdf/1906.01470v2.pdf
PWC	https://paperswithcode.com/paper/options-as-responses-grounding-behavioural
Repo	https://github.com/YuhangSong/Arena-BuildingToolkit
Framework	none

Counterfactual Risk Assessments, Evaluation, and Fairness


Title	Counterfactual Risk Assessments, Evaluation, and Fairness
Authors	Amanda Coston, Alan Mishler, Edward H. Kennedy, Alexandra Chouldechova
Abstract	Algorithmic risk assessments are increasingly used to help humans make decisions in high-stakes settings, such as medicine, criminal justice and education. In each of these cases, the purpose of the risk assessment tool is to inform actions, such as medical treatments or release conditions, often with the aim of reducing the likelihood of an adverse event such as hospital readmission or recidivism. Problematically, most tools are trained and evaluated on historical data in which the outcomes observed depend on the historical decision-making policy. These tools thus reflect risk under the historical policy, rather than under the different decision options that the tool is intended to inform. Even when tools are constructed to predict risk under a specific decision, they are often improperly evaluated as predictors of the target outcome. Focusing on the evaluation task, in this paper we define counterfactual analogues of common predictive performance and algorithmic fairness metrics that we argue are better suited for the decision-making context. We introduce a new method for estimating the proposed metrics using doubly robust estimation. We provide theoretical results that show that only under strong conditions can fairness according to the standard metric and the counterfactual metric simultaneously hold. Consequently, fairness-promoting methods that target parity in a standard fairness metric may — and as we show empirically, do — induce greater imbalance in the counterfactual analogue. We provide empirical comparisons on both synthetic data and a real world child welfare dataset to demonstrate how the proposed method improves upon standard practice.
Tasks	Decision Making
Published	2019-08-30
URL	https://arxiv.org/abs/1909.00066v3
PDF	https://arxiv.org/pdf/1909.00066v3.pdf
PWC	https://paperswithcode.com/paper/counterfactual-risk-assessments-evaluation
Repo	https://github.com/mandycoston/counterfactual
Framework	none

Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence


Title	Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence
Authors	Yuhang Song, Andrzej Wojcicki, Thomas Lukasiewicz, Jianyi Wang, Abi Aryan, Zhenghua Xu, Mai Xu, Zihan Ding, Lianlong Wu
Abstract	Learning agents that are not only capable of taking tests, but also innovating is becoming a hot topic in AI. One of the most promising paths towards this vision is multi-agent learning, where agents act as the environment for each other, and improving each agent means proposing new problems for others. However, existing evaluation platforms are either not compatible with multi-agent settings, or limited to a specific game. That is, there is not yet a general evaluation platform for research on multi-agent intelligence. To this end, we introduce Arena, a general evaluation platform for multi-agent intelligence with 35 games of diverse logics and representations. Furthermore, multi-agent intelligence is still at the stage where many problems remain unexplored. Therefore, we provide a building toolkit for researchers to easily invent and build novel multi-agent problems from the provided game set based on a GUI-configurable social tree and five basic multi-agent reward schemes. Finally, we provide Python implementations of five state-of-the-art deep multi-agent reinforcement learning baselines. Along with the baseline implementations, we release a set of 100 best agents/teams that we can train with different training schemes for each game, as the base for evaluating agents with population performance. As such, the research community can perform comparisons under a stable and uniform standard. All the implementations and accompanied tutorials have been open-sourced for the community at https://sites.google.com/view/arena-unity/.
Tasks	Multi-agent Reinforcement Learning
Published	2019-05-17
URL	https://arxiv.org/abs/1905.08085v5
PDF	https://arxiv.org/pdf/1905.08085v5.pdf
PWC	https://paperswithcode.com/paper/arena-a-general-evaluation-platform-and
Repo	https://github.com/YuhangSong/Arena-Baselines
Framework	pytorch

Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling


Title	Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
Authors	Jonathan Shen, Patrick Nguyen, Yonghui Wu, Zhifeng Chen, Mia X. Chen, Ye Jia, Anjuli Kannan, Tara Sainath, Yuan Cao, Chung-Cheng Chiu, Yanzhang He, Jan Chorowski, Smit Hinsu, Stella Laurenzo, James Qin, Orhan Firat, Wolfgang Macherey, Suyog Gupta, Ankur Bapna, Shuyuan Zhang, Ruoming Pang, Ron J. Weiss, Rohit Prabhavalkar, Qiao Liang, Benoit Jacob, Bowen Liang, HyoukJoong Lee, Ciprian Chelba, Sébastien Jean, Bo Li, Melvin Johnson, Rohan Anil, Rajat Tibrewal, Xiaobing Liu, Akiko Eriguchi, Navdeep Jaitly, Naveen Ari, Colin Cherry, Parisa Haghani, Otavio Good, Youlong Cheng, Raziel Alvarez, Isaac Caswell, Wei-Ning Hsu, Zongheng Yang, Kuan-Chieh Wang, Ekaterina Gonina, Katrin Tomanek, Ben Vanik, Zelin Wu, Llion Jones, Mike Schuster, Yanping Huang, Dehao Chen, Kazuki Irie, George Foster, John Richardson, Klaus Macherey, Antoine Bruguier, Heiga Zen, Colin Raffel, Shankar Kumar, Kanishka Rao, David Rybach, Matthew Murray, Vijayaditya Peddinti, Maxim Krikun, Michiel A. U. Bacchiani, Thomas B. Jablin, Rob Suderman, Ian Williams, Benjamin Lee, Deepti Bhatia, Justin Carlson, Semih Yavuz, Yu Zhang, Ian McGraw, Max Galkin, Qi Ge, Golan Pundak, Chad Whipkey, Todd Wang, Uri Alon, Dmitry Lepikhin, Ye Tian, Sara Sabour, William Chan, Shubham Toshniwal, Baohua Liao, Michael Nirschl, Pat Rondon
Abstract	Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models. Lingvo models are composed of modular building blocks that are flexible and easily extensible, and experiment configurations are centralized and highly customizable. Distributed training and quantized inference are supported directly within the framework, and it contains existing implementations of a large number of utilities, helper functions, and the newest research ideas. Lingvo has been used in collaboration by dozens of researchers in more than 20 papers over the last two years. This document outlines the underlying design of Lingvo and serves as an introduction to the various pieces of the framework, while also offering examples of advanced features that showcase the capabilities of the framework.
Tasks	Sequence-To-Sequence Speech Recognition
Published	2019-02-21
URL	http://arxiv.org/abs/1902.08295v1
PDF	http://arxiv.org/pdf/1902.08295v1.pdf
PWC	https://paperswithcode.com/paper/lingvo-a-modular-and-scalable-framework-for
Repo	https://github.com/tensorflow/lingvo
Framework	tf

A review on Deep Reinforcement Learning for Fluid Mechanics


Title	A review on Deep Reinforcement Learning for Fluid Mechanics
Authors	Paul Garnier, Jonathan Viquerat, Jean Rabault, Aurélien Larcher, Alexander Kuhnle, Elie Hachem
Abstract	Deep reinforcement learning (DRL) has recently been adopted in a wide range of physics and engineering domains for its ability to solve decision-making problems that were previously out of reach due to a combination of non-linearity and high dimensionality. In the last few years, it has spread in the field of computational mechanics, and particularly in fluid dynamics, with recent applications in flow control and shape optimization. In this work, we conduct a detailed review of existing DRL applications to fluid mechanics problems. In addition, we present recent results that further illustrate the potential of DRL in Fluid Mechanics. The coupling methods used in each case are covered, detailing their advantages and limitations. Our review also focuses on the comparison with classical methods for optimal control and optimization. Finally, several test cases are described that illustrate recent progress made in this field. The goal of this publication is to provide an understanding of DRL capabilities along with state-of-the-art applications in fluid dynamics to researchers wishing to address new problems with these methods.
Tasks	Decision Making
Published	2019-08-12
URL	https://arxiv.org/abs/1908.04127v1
PDF	https://arxiv.org/pdf/1908.04127v1.pdf
PWC	https://paperswithcode.com/paper/a-review-on-deep-reinforcement-learning-for
Repo	https://github.com/DonsetPG/fenics-DRL
Framework	tf

Shapley Q-value: A Local Reward Approach to Solve Global Reward Games


Title	Shapley Q-value: A Local Reward Approach to Solve Global Reward Games
Authors	Jianhong Wang, Yuan Zhang, Tae-Kyun Kim, Yunjie Gu
Abstract	Cooperative game is a critical research area in the multi-agent reinforcement learning (MARL). Global reward game is a subclass of cooperative games, where all agents aim to maximize the global reward. Credit assignment is an important problem studied in the global reward game. Most of previous works stood by the view of non-cooperative-game theoretical framework with the shared reward approach, i.e., each agent being assigned a shared global reward directly. This, however, may give each agent an inaccurate reward on its contribution to the group, which could cause inefficient learning. To deal with this problem, we i) introduce a cooperative-game theoretical framework called extended convex game (ECG) that is a superset of global reward game, and ii) propose a local reward approach called Shapley Q-value. Shapley Q-value is able to distribute the global reward, reflecting each agent’s own contribution in contrast to the shared reward approach. Moreover, we derive an MARL algorithm called Shapley Q-value deep deterministic policy gradient (SQDDPG), using Shapley Q-value as the critic for each agent. We evaluate SQDDPG on Cooperative Navigation, Prey-and-Predator and Traffic Junction, compared with the state-of-the-art algorithms, e.g., MADDPG, COMA, Independent DDPG and Independent A2C. In the experiments, SQDDPG shows a significant improvement on the convergence rate. Finally, we plot Shapley Q-value and validate the property of fair credit assignment.
Tasks	Multi-agent Reinforcement Learning, Policy Gradient Methods
Published	2019-07-11
URL	https://arxiv.org/abs/1907.05707v4
PDF	https://arxiv.org/pdf/1907.05707v4.pdf
PWC	https://paperswithcode.com/paper/rethink-global-reward-game-and-credit
Repo	https://github.com/hsvgbkhgbv/SQDDPG
Framework	pytorch

Semi-supervised Compatibility Learning Across Categories for Clothing Matching


Title	Semi-supervised Compatibility Learning Across Categories for Clothing Matching
Authors	Zekun Li, Zeyu Cui, Shu Wu, Xiaoyu Zhang, Liang Wang
Abstract	Learning the compatibility between fashion items across categories is a key task in fashion analysis, which can decode the secret of clothing matching. The main idea of this task is to map items into a latent style space where compatible items stay close. Previous works try to build such a transformation by minimizing the distances between annotated compatible items, which require massive item-level supervision. However, these annotated data are expensive to obtain and hard to cover the numerous items with various styles in real applications. In such cases, these supervised methods fail to achieve satisfactory performances. In this work, we propose a semi-supervised method to learn the compatibility across categories. We observe that the distributions of different categories have intrinsic similar structures. Accordingly, the better distributions align, the closer compatible items across these categories become. To achieve the alignment, we minimize the distances between distributions with unsupervised adversarial learning, and also the distances between some annotated compatible items which play the role of anchor points to help align. Experimental results on two real-world datasets demonstrate the effectiveness of our method.
Tasks
Published	2019-07-31
URL	https://arxiv.org/abs/1907.13304v1
PDF	https://arxiv.org/pdf/1907.13304v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-compatibility-learning-across
Repo	https://github.com/CRIPAC-DIG/SCGAN
Framework	tf

A Provable Defense for Deep Residual Networks


Title	A Provable Defense for Deep Residual Networks
Authors	Matthew Mirman, Gagandeep Singh, Martin Vechev
Abstract	We present a training system, which can provably defend significantly larger neural networks than previously possible, including ResNet-34 and DenseNet-100. Our approach is based on differentiable abstract interpretation and introduces two novel concepts: (i) abstract layers for fine-tuning the precision and scalability of the abstraction, (ii) a flexible domain specific language (DSL) for describing training objectives that combine abstract and concrete losses with arbitrary specifications. Our training method is implemented in the DiffAI system.
Tasks	Adversarial Defense
Published	2019-03-29
URL	https://arxiv.org/abs/1903.12519v2
PDF	https://arxiv.org/pdf/1903.12519v2.pdf
PWC	https://paperswithcode.com/paper/a-provable-defense-for-deep-residual-networks
Repo	https://github.com/eth-sri/diffai
Framework	pytorch

Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch Noise


Title	Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch Noise
Authors	Senwei Liang, Zhongzhan Huang, Mingfu Liang, Haizhao Yang
Abstract	Batch Normalization (BN)(Ioffe and Szegedy 2015) normalizes the features of an input image via statistics of a batch of images and hence BN will bring the noise to the gradient of the training loss. Previous works indicate that the noise is important for the optimization and generalization of deep neural networks, but too much noise will harm the performance of networks. In our paper, we offer a new point of view that self-attention mechanism can help to regulate the noise by enhancing instance-specific information to obtain a better regularization effect. Therefore, we propose an attention-based BN called Instance Enhancement Batch Normalization (IEBN) that recalibrates the information of each channel by a simple linear transformation. IEBN has a good capacity of regulating noise and stabilizing network training to improve generalization even in the presence of two kinds of noise attacks during training. Finally, IEBN outperforms BN with only a light parameter increment in image classification tasks for different network structures and benchmark datasets.
Tasks	Image Classification
Published	2019-08-12
URL	https://arxiv.org/abs/1908.04008v2
PDF	https://arxiv.org/pdf/1908.04008v2.pdf
PWC	https://paperswithcode.com/paper/instance-enhancement-batch-normalization-an
Repo	https://github.com/gbup-group/IEBN
Framework	pytorch

Jointly Extracting and Compressing Documents with Summary State Representations


Title	Jointly Extracting and Compressing Documents with Summary State Representations
Authors	Afonso Mendes, Shashi Narayan, Sebastião Miranda, Zita Marinho, André F. T. Martins, Shay B. Cohen
Abstract	We present a new neural model for text summarization that first extracts sentences from a document and then compresses them. The proposed model offers a balance that sidesteps the difficulties in abstractive methods while generating more concise summaries than extractive methods. In addition, our model dynamically determines the length of the output summary based on the gold summaries it observes during training and does not require length constraints typical to extractive summarization. The model achieves state-of-the-art results on the CNN/DailyMail and Newsroom datasets, improving over current extractive and abstractive methods. Human evaluations demonstrate that our model generates concise and informative summaries. We also make available a new dataset of oracle compressive summaries derived automatically from the CNN/DailyMail reference summaries.
Tasks	Text Summarization
Published	2019-04-03
URL	http://arxiv.org/abs/1904.02020v2
PDF	http://arxiv.org/pdf/1904.02020v2.pdf
PWC	https://paperswithcode.com/paper/jointly-extracting-and-compressing
Repo	https://github.com/Priberam/exconsumm
Framework	none