January 31, 2020

3279 words 16 mins read

Paper Group ANR 119

Multi-Agent Game Abstraction via Graph Attention Neural Network. Predicting Food Security Outcomes Using Convolutional Neural Networks (CNNs) for Satellite Tasking. Location Trace Privacy Under Conditional Priors. Learning 3D Navigation Protocols on Touch Interfaces with Cooperative Multi-Agent Reinforcement Learning. Agora: Towards An Open Ecosyst …

Multi-Agent Game Abstraction via Graph Attention Neural Network


Title	Multi-Agent Game Abstraction via Graph Attention Neural Network
Authors	Yong Liu, Weixun Wang, Yujing Hu, Jianye Hao, Xingguo Chen, Yang Gao
Abstract	In large-scale multi-agent systems, the large number of agents and complex game relationship cause great difficulty for policy learning. Therefore, simplifying the learning process is an important research issue. In many multi-agent systems, the interactions between agents often happen locally, which means that agents neither need to coordinate with all other agents nor need to coordinate with others all the time. Traditional methods attempt to use pre-defined rules to capture the interaction relationship between agents. However, the methods cannot be directly used in a large-scale environment due to the difficulty of transforming the complex interactions between agents into rules. In this paper, we model the relationship between agents by a complete graph and propose a novel game abstraction mechanism based on two-stage attention network (G2ANet), which can indicate whether there is an interaction between two agents and the importance of the interaction. We integrate this detection mechanism into graph neural network-based multi-agent reinforcement learning for conducting game abstraction and propose two novel learning algorithms GA-Comm and GA-AC. We conduct experiments in Traffic Junction and Predator-Prey. The results indicate that the proposed methods can simplify the learning process and meanwhile get better asymptotic performance compared with state-of-the-art algorithms.
Tasks	Multi-agent Reinforcement Learning
Published	2019-11-25
URL	https://arxiv.org/abs/1911.10715v1
PDF	https://arxiv.org/pdf/1911.10715v1.pdf
PWC	https://paperswithcode.com/paper/multi-agent-game-abstraction-via-graph
Repo
Framework

Predicting Food Security Outcomes Using Convolutional Neural Networks (CNNs) for Satellite Tasking


Title	Predicting Food Security Outcomes Using Convolutional Neural Networks (CNNs) for Satellite Tasking
Authors	Swetava Ganguli, Jared Dunnmon, Darren Hau
Abstract	Obtaining reliable data describing local Food Security Metrics (FSM) at a granularity that is informative to policy-makers requires expensive and logistically difficult surveys, particularly in the developing world. We train a CNN on publicly available satellite data describing land cover classification and use both transfer learning and direct training to build a model for FSM prediction purely from satellite imagery data. We then propose efficient tasking algorithms for high resolution satellite assets via transfer learning, Markovian search algorithms, and Bayesian networks.
Tasks	Transfer Learning
Published	2019-02-13
URL	http://arxiv.org/abs/1902.05433v2
PDF	http://arxiv.org/pdf/1902.05433v2.pdf
PWC	https://paperswithcode.com/paper/predicting-food-security-outcomes-using
Repo
Framework

Location Trace Privacy Under Conditional Priors


Title	Location Trace Privacy Under Conditional Priors
Authors	Casey Meehan, Kamalika Chaudhuri
Abstract	Providing meaningful privacy to users of location based services is particularly challenging when multiple locations are revealed in a short period of time. This is primarily due to the tremendous degree of dependence that can be anticipated between points. We propose a R'enyi differentially private framework for bounding expected privacy loss for conditionally dependent data. Additionally, we demonstrate an algorithm for achieving this privacy under Gaussian process conditional priors. This framework both exemplifies why conditionally dependent data is so challenging to protect and offers a strategy for preserving privacy to within a fixed radius for every user location in a trace.
Tasks
Published	2019-12-09
URL	https://arxiv.org/abs/1912.04228v1
PDF	https://arxiv.org/pdf/1912.04228v1.pdf
PWC	https://paperswithcode.com/paper/location-trace-privacy-under-conditional
Repo
Framework


Title	Learning 3D Navigation Protocols on Touch Interfaces with Cooperative Multi-Agent Reinforcement Learning
Authors	Quentin Debard, Jilles Steeve Dibangoye, Stéphane Canu, Christian Wolf
Abstract	Using touch devices to navigate in virtual 3D environments such as computer assisted design (CAD) models or geographical information systems (GIS) is inherently difficult for humans, as the 3D operations have to be performed by the user on a 2D touch surface. This ill-posed problem is classically solved with a fixed and handcrafted interaction protocol, which must be learned by the user. We propose to automatically learn a new interaction protocol allowing to map a 2D user input to 3D actions in virtual environments using reinforcement learning (RL). A fundamental problem of RL methods is the vast amount of interactions often required, which are difficult to come by when humans are involved. To overcome this limitation, we make use of two collaborative agents. The first agent models the human by learning to perform the 2D finger trajectories. The second agent acts as the interaction protocol, interpreting and translating to 3D operations the 2D finger trajectories from the first agent. We restrict the learned 2D trajectories to be similar to a training set of collected human gestures by first performing state representation learning, prior to reinforcement learning. This state representation learning is addressed by projecting the gestures into a latent space learned by a variational auto encoder (VAE).
Tasks	Multi-agent Reinforcement Learning, Representation Learning
Published	2019-04-16
URL	https://arxiv.org/abs/1904.07802v2
PDF	https://arxiv.org/pdf/1904.07802v2.pdf
PWC	https://paperswithcode.com/paper/learning-3d-navigation-protocols-on-touch
Repo
Framework

Agora: Towards An Open Ecosystem for Democratizing Data Science & Artificial Intelligence


Title	Agora: Towards An Open Ecosystem for Democratizing Data Science & Artificial Intelligence
Authors	Jonas Traub, Jorge-Arnulfo Quiané-Ruiz, Zoi Kaoudi, Volker Markl
Abstract	Data science and artificial intelligence are driven by a plethora of diverse data-related assets including datasets, data streams, algorithms, processing software, compute resources, and domain knowledge. As providing all these assets requires a huge investment, data sciences and artificial intelligence are currently dominated by a small number of providers who can afford these investments. In this paper, we present a vision of a data ecosystem to democratize data science and artificial intelligence. In particular, we envision a data infrastructure for fine-grained asset exchange in combination with scalable systems operation. This will overcome lock-in effects and remove entry barriers for new asset providers. Our goal is to enable companies, research organizations, and individuals to have equal access to data, data science, and artificial intelligence. Such an open ecosystem has recently been put on the agenda of several governments and industrial associations. We point out the requirements and the research challenges as well as outline an initial data infrastructure architecture for building such a data ecosystem.
Tasks
Published	2019-09-06
URL	https://arxiv.org/abs/1909.03026v2
PDF	https://arxiv.org/pdf/1909.03026v2.pdf
PWC	https://paperswithcode.com/paper/agora-towards-an-open-ecosystem-for
Repo
Framework

Automated Enriched Medical Concept Generation for Chest X-ray Images


Title	Automated Enriched Medical Concept Generation for Chest X-ray Images
Authors	Aydan Gasimova
Abstract	Decision support tools that rely on supervised learning require large amounts of expert annotations. Using past radiological reports obtained from hospital archiving systems has many advantages as training data above manual single-class labels: they are expert annotations available in large quantities, covering a population-representative variety of pathologies, and they provide additional context to pathology diagnoses, such as anatomical location and severity. Learning to auto-generate such reports from images present many challenges such as the difficulty in representing and generating long, unstructured textual information, accounting for spelling errors and repetition/redundancy, and the inconsistency across different annotators. We therefore propose to first learn visually-informative medical concepts from raw reports, and, using the concept predictions as image annotations, learn to auto-generate structured reports directly from images. We validate our approach on the OpenI [2] chest x-ray dataset, which consists of frontal and lateral views of chest x-ray images, their corresponding raw textual reports and manual medical subject heading (MeSH ) annotations made by radiologists.
Tasks
Published	2019-10-07
URL	https://arxiv.org/abs/1910.02935v1
PDF	https://arxiv.org/pdf/1910.02935v1.pdf
PWC	https://paperswithcode.com/paper/automated-enriched-medical-concept-generation
Repo
Framework

Cross-Corpora Evaluation and Analysis of Grammatical Error Correction Models — Is Single-Corpus Evaluation Enough?


Title	Cross-Corpora Evaluation and Analysis of Grammatical Error Correction Models — Is Single-Corpus Evaluation Enough?
Authors	Masato Mita, Tomoya Mizumoto, Masahiro Kaneko, Ryo Nagata, Kentaro Inui
Abstract	This study explores the necessity of performing cross-corpora evaluation for grammatical error correction (GEC) models. GEC models have been previously evaluated based on a single commonly applied corpus: the CoNLL-2014 benchmark. However, the evaluation remains incomplete because the task difficulty varies depending on the test corpus and conditions such as the proficiency levels of the writers and essay topics. To overcome this limitation, we evaluate the performance of several GEC models, including NMT-based (LSTM, CNN, and transformer) and an SMT-based model, against various learner corpora (CoNLL-2013, CoNLL-2014, FCE, JFLEG, ICNALE, and KJ). Evaluation results reveal that the models’ rankings considerably vary depending on the corpus, indicating that single-corpus evaluation is insufficient for GEC models.
Tasks	Grammatical Error Correction
Published	2019-04-05
URL	http://arxiv.org/abs/1904.02927v1
PDF	http://arxiv.org/pdf/1904.02927v1.pdf
PWC	https://paperswithcode.com/paper/cross-corpora-evaluation-and-analysis-of
Repo
Framework

Efficient Detection and Quantification of Timing Leaks with Neural Networks


Title	Efficient Detection and Quantification of Timing Leaks with Neural Networks
Authors	Saeid Tizpaz-Niari, Pavol Cerny, Sriram Sankaranarayanan, Ashutosh Trivedi
Abstract	Detection and quantification of information leaks through timing side channels are important to guarantee confidentiality. Although static analysis remains the prevalent approach for detecting timing side channels, it is computationally challenging for real-world applications. In addition, the detection techniques are usually restricted to ‘yes’ or ‘no’ answers. In practice, real-world applications may need to leak information about the secret. Therefore, quantification techniques are necessary to evaluate the resulting threats of information leaks. Since both problems are very difficult or impossible for static analysis techniques, we propose a dynamic analysis method. Our novel approach is to split the problem into two tasks. First, we learn a timing model of the program as a neural network. Second, we analyze the neural network to quantify information leaks. As demonstrated in our experiments, both of these tasks are feasible in practice — making the approach a significant improvement over the state-of-the-art side channel detectors and quantifiers. Our key technical contributions are (a) a neural network architecture that enables side channel discovery and (b) an MILP-based algorithm to estimate the side-channel strength. On a set of micro-benchmarks and real-world applications, we show that neural network models learn timing behaviors of programs with thousands of methods. We also show that neural networks with thousands of neurons can be efficiently analyzed to detect and quantify information leaks through timing side channels.
Tasks
Published	2019-07-23
URL	https://arxiv.org/abs/1907.10159v1
PDF	https://arxiv.org/pdf/1907.10159v1.pdf
PWC	https://paperswithcode.com/paper/efficient-detection-and-quantification-of
Repo
Framework

2D Attentional Irregular Scene Text Recognizer


Title	2D Attentional Irregular Scene Text Recognizer
Authors	Pengyuan Lyu, Zhicheng Yang, Xinhang Leng, Xiaojun Wu, Ruiyu Li, Xiaoyong Shen
Abstract	Irregular scene text, which has complex layout in 2D space, is challenging to most previous scene text recognizers. Recently, some irregular scene text recognizers either rectify the irregular text to regular text image with approximate 1D layout or transform the 2D image feature map to 1D feature sequence. Though these methods have achieved good performance, the robustness and accuracy are still limited due to the loss of spatial information in the process of 2D to 1D transformation. Different from all of previous, we in this paper propose a framework which transforms the irregular text with 2D layout to character sequence directly via 2D attentional scheme. We utilize a relation attention module to capture the dependencies of feature maps and a parallel attention module to decode all characters in parallel, which make our method more effective and efficient. Extensive experiments on several public benchmarks as well as our collected multi-line text dataset show that our approach is effective to recognize regular and irregular scene text and outperforms previous methods both in accuracy and speed.
Tasks
Published	2019-06-13
URL	https://arxiv.org/abs/1906.05708v1
PDF	https://arxiv.org/pdf/1906.05708v1.pdf
PWC	https://paperswithcode.com/paper/2d-attentional-irregular-scene-text
Repo
Framework

BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization


Title	BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization
Authors	Yuyang Gao, Giorgio Ascoli, Liang Zhao
Abstract	Deep neural networks (DNNs) are known for extracting good representations from a large amount of data. However, the representations learned in DNNs are typically hard to interpret, especially the ones learned in dense layers. One crucial issue is that neurons within each layer of DNNs are conditionally independent with each other, which makes the co-training and analysis of neurons at higher modularity difficult. In contrast, the dependency patterns of biological neurons in the human brain are largely different from those of DNNs. Neuronal assembly describes such neuron dependencies that could be found among a group of biological neurons as having strong internal synaptic interactions, potentially high semantical correlations that are deemed to facilitate the memorization process. In this paper, we show such a crucial gap between DNNs and biological neural networks (BNNs) can be bridged by the newly proposed Biologically-Enhanced Artificial Neuronal assembly (BEAN) regularization that could enforce dependencies among neurons in dense layers of DNNs without altering the conventional architecture. Both qualitative and quantitative analyses show that BEAN enables the formations of interpretable and biologically plausible neuronal assemblies in dense layers and consequently enhances the modularity and interpretability of the hidden representations learned. Moreover, BEAN further results in sparse and structured connectivity and parameter sharing among neurons, which substantially improves the efficiency and generalizability of the model.
Tasks	Representation Learning
Published	2019-09-27
URL	https://arxiv.org/abs/1909.13698v1
PDF	https://arxiv.org/pdf/1909.13698v1.pdf
PWC	https://paperswithcode.com/paper/bean-interpretable-representation-learning
Repo
Framework

FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network


Title	FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network
Authors	Zeeshan Khan, Mukul Khanna, Shanmuganathan Raman
Abstract	High dynamic range (HDR) image generation from a single exposure low dynamic range (LDR) image has been made possible due to the recent advances in Deep Learning. Various feed-forward Convolutional Neural Networks (CNNs) have been proposed for learning LDR to HDR representations. To better utilize the power of CNNs, we exploit the idea of feedback, where the initial low level features are guided by the high level features using a hidden state of a Recurrent Neural Network. Unlike a single forward pass in a conventional feed-forward network, the reconstruction from LDR to HDR in a feedback network is learned over multiple iterations. This enables us to create a coarse-to-fine representation, leading to an improved reconstruction at every iteration. Various advantages over standard feed-forward networks include early reconstruction ability and better reconstruction quality with fewer network parameters. We design a dense feedback block and propose an end-to-end feedback network- FHDR for HDR image generation from a single exposure LDR image. Qualitative and quantitative evaluations show the superiority of our approach over the state-of-the-art methods.
Tasks	Image Generation, Image Reconstruction
Published	2019-12-24
URL	https://arxiv.org/abs/1912.11463v1
PDF	https://arxiv.org/pdf/1912.11463v1.pdf
PWC	https://paperswithcode.com/paper/fhdr-hdr-image-reconstruction-from-a-single
Repo
Framework

KPTransfer: improved performance and faster convergence from keypoint subset-wise domain transfer in human pose estimation


Title	KPTransfer: improved performance and faster convergence from keypoint subset-wise domain transfer in human pose estimation
Authors	Kanav Vats, Helmut Neher, Alexander Wong, David A. Clausi, John Zelek
Abstract	In this paper, we present a novel approach called KPTransfer for improving modeling performance for keypoint detection deep neural networks via domain transfer between different keypoint subsets. This approach is motivated by the notion that rich contextual knowledge can be transferred between different keypoint subsets representing separate domains. In particular, the proposed method takes into account various keypoint subsets/domains by sequentially adding and removing keypoints. Contextual knowledge is transferred between two separate domains via domain transfer. Experiments to demonstrate the efficacy of the proposed KPTransfer approach were performed for the task of human pose estimation on the MPII dataset, with comparisons against random initialization and frozen weight extraction configurations. Experimental results demonstrate the efficacy of performing domain transfer between two different joint subsets resulting in a PCKh improvement of up to 1.1 over random initialization on joints such as wrists and knee in certain joint splits with an overall PCKh improvement of 0.5. Domain transfer from a different set of joints not only results in improved accuracy but also results in faster convergence because of mutual co-adaptations of weights resulting from the contextual knowledge of the pose from a different set of joints.
Tasks	Keypoint Detection, Pose Estimation
Published	2019-03-24
URL	http://arxiv.org/abs/1903.09926v1
PDF	http://arxiv.org/pdf/1903.09926v1.pdf
PWC	https://paperswithcode.com/paper/kptransfer-improved-performance-and-faster
Repo
Framework

Adversarial symmetric GANs: bridging adversarial samples and adversarial networks


Title	Adversarial symmetric GANs: bridging adversarial samples and adversarial networks
Authors	Faqiang Liu, Mingkun Xu, Guoqi Li, Jing Pei, Luping Shi, Rong Zhao
Abstract	Generative adversarial networks have achieved remarkable performance on various tasks but suffer from training instability. Despite many training strategies proposed to improve training stability, this issue remains as a challenge. In this paper, we investigate the training instability from the perspective of adversarial samples and reveal that adversarial training on fake samples is implemented in vanilla GANs, but adversarial training on real samples has long been overlooked. Consequently, the discriminator is extremely vulnerable to adversarial perturbation and the gradient given by the discriminator contains non-informative adversarial noises, which hinders the generator from catching the pattern of real samples. Here, we develop adversarial symmetric GANs (AS-GANs) that incorporate adversarial training of the discriminator on real samples into vanilla GANs, making adversarial training symmetrical. The discriminator is therefore more robust and provides more informative gradient with less adversarial noise, thereby stabilizing training and accelerating convergence. The effectiveness of the AS-GANs is verified on image generation on CIFAR-10 , CelebA, and LSUN with varied network architectures. Not only the training is more stabilized, but the FID scores of generated samples are consistently improved by a large margin compared to the baseline. The bridging of adversarial samples and adversarial networks provides a new approach to further develop adversarial networks.
Tasks	Image Generation
Published	2019-12-20
URL	https://arxiv.org/abs/1912.09670v2
PDF	https://arxiv.org/pdf/1912.09670v2.pdf
PWC	https://paperswithcode.com/paper/bridging-adversarial-samples-and-adversarial-1
Repo
Framework

Generation of Multimodal Justification Using Visual Word Constraint Model for Explainable Computer-Aided Diagnosis


Title	Generation of Multimodal Justification Using Visual Word Constraint Model for Explainable Computer-Aided Diagnosis
Authors	Hyebin Lee, Seong Tae Kim, Yong Man Ro
Abstract	The ambiguity of the decision-making process has been pointed out as the main obstacle to applying the deep learning-based method in a practical way in spite of its outstanding performance. Interpretability could guarantee the confidence of deep learning system, therefore it is particularly important in the medical field. In this study, a novel deep network is proposed to explain the diagnostic decision with visual pointing map and diagnostic sentence justifying result simultaneously. For the purpose of increasing the accuracy of sentence generation, a visual word constraint model is devised in training justification generator. To verify the proposed method, comparative experiments were conducted on the problem of the diagnosis of breast masses. Experimental results demonstrated that the proposed deep network could explain diagnosis more accurately with various textual justifications.
Tasks	Decision Making
Published	2019-06-10
URL	https://arxiv.org/abs/1906.03922v1
PDF	https://arxiv.org/pdf/1906.03922v1.pdf
PWC	https://paperswithcode.com/paper/generation-of-multimodal-justification-using
Repo
Framework

Improving Robustness In Speaker Identification Using A Two-Stage Attention Model


Title	Improving Robustness In Speaker Identification Using A Two-Stage Attention Model
Authors	Yanpei Shi, Qiang Huang, Thomas Hain
Abstract	In this paper a novel framework to tackle speaker recognition using a two-stage attention model is proposed. In recent years, the use of deep neural networks, such as time delay neural network (TDNN), and attention model have boosted speaker recognition performance. However, it is still a challenging task to tackle speaker recognition in severe acoustic environments. To build a robust speaker recognition system against noise, we employ a two-stage attention model and combine it with a TDNN model. In this framework, the attention mechanism is used in two aspects: embedding space and temporal space. The embedding attention model built in embedding space is to highlight the importance of each embedding element by weighting them using self attention. The frame attention model built in temporal space aims to find which frames are significant for speaker recognition. To evaluate the effectiveness and robustness of our approach, we use the TIMIT dataset and test our approach in the condition of five kinds of noise and different signal-noise-ratios (SNRs). In comparison with three strong baselines, CNN, TDNN and TDNN+attention, the experimental results show that the use of our approach outperforms them in different conditions. The correct recognition rate obtained using our approach can still reach 49.1%, better than any baselines, even if the noise is Gaussian white Noise and the SNR is 0dB.
Tasks	Speaker Identification, Speaker Recognition
Published	2019-09-24
URL	https://arxiv.org/abs/1909.11200v1
PDF	https://arxiv.org/pdf/1909.11200v1.pdf
PWC	https://paperswithcode.com/paper/improving-robustness-in-speaker
Repo
Framework