October 20, 2019

3176 words 15 mins read

Paper Group AWR 263

Multivariate Convolutional Sparse Coding for Electromagnetic Brain Signals. Fighting Fire with Fire: Using Antidote Data to Improve Polarization and Fairness of Recommender Systems. ExIt-OOS: Towards Learning from Planning in Imperfect Information Games. Communication Algorithms via Deep Learning. A Full End-to-End Semantic Role Labeler, Syntax-agn …

Multivariate Convolutional Sparse Coding for Electromagnetic Brain Signals


Title	Multivariate Convolutional Sparse Coding for Electromagnetic Brain Signals
Authors	Tom Dupré La Tour, Thomas Moreau, Mainak Jas, Alexandre Gramfort
Abstract	Frequency-specific patterns of neural activity are traditionally interpreted as sustained rhythmic oscillations, and related to cognitive mechanisms such as attention, high level visual processing or motor control. While alpha waves (8-12 Hz) are known to closely resemble short sinusoids, and thus are revealed by Fourier analysis or wavelet transforms, there is an evolving debate that electromagnetic neural signals are composed of more complex waveforms that cannot be analyzed by linear filters and traditional signal representations. In this paper, we propose to learn dedicated representations of such recordings using a multivariate convolutional sparse coding (CSC) algorithm. Applied to electroencephalography (EEG) or magnetoencephalography (MEG) data, this method is able to learn not only prototypical temporal waveforms, but also associated spatial patterns so their origin can be localized in the brain. Our algorithm is based on alternated minimization and a greedy coordinate descent solver that leads to state-of-the-art running time on long time series. To demonstrate the implications of this method, we apply it to MEG data and show that it is able to recover biological artifacts. More remarkably, our approach also reveals the presence of non-sinusoidal mu-shaped patterns, along with their topographic maps related to the somatosensory cortex.
Tasks	EEG, Time Series
Published	2018-05-24
URL	http://arxiv.org/abs/1805.09654v2
PDF	http://arxiv.org/pdf/1805.09654v2.pdf
PWC	https://paperswithcode.com/paper/multivariate-convolutional-sparse-coding-for
Repo	https://github.com/alphacsc/alphacsc
Framework	none

Fighting Fire with Fire: Using Antidote Data to Improve Polarization and Fairness of Recommender Systems


Title	Fighting Fire with Fire: Using Antidote Data to Improve Polarization and Fairness of Recommender Systems
Authors	Bashir Rastegarpanah, Krishna P. Gummadi, Mark Crovella
Abstract	The increasing role of recommender systems in many aspects of society makes it essential to consider how such systems may impact social good. Various modifications to recommendation algorithms have been proposed to improve their performance for specific socially relevant measures. However, previous proposals are often not easily adapted to different measures, and they generally require the ability to modify either existing system inputs, the system’s algorithm, or the system’s outputs. As an alternative, in this paper we introduce the idea of improving the social desirability of recommender system outputs by adding more data to the input, an approach we view as providing `antidote’ data to the system. We formalize the antidote data problem, and develop optimization-based solutions. We take as our model system the matrix factorization approach to recommendation, and we propose a set of measures to capture the polarization or fairness of recommendations. We then show how to generate antidote data for each measure, pointing out a number of computational efficiencies, and discuss the impact on overall system accuracy. Our experiments show that a modest budget for antidote data can lead to significant improvements in the polarization or fairness of recommendations. \|
Tasks	Recommendation Systems
Published	2018-12-02
URL	http://arxiv.org/abs/1812.01504v4
PDF	http://arxiv.org/pdf/1812.01504v4.pdf
PWC	https://paperswithcode.com/paper/fighting-fire-with-fire-using-antidote-data
Repo	https://github.com/rastegarpanah/antidote-data-framework
Framework	none

ExIt-OOS: Towards Learning from Planning in Imperfect Information Games


Title	ExIt-OOS: Towards Learning from Planning in Imperfect Information Games
Authors	Andy Kitchen, Michela Benedetti
Abstract	The current state of the art in playing many important perfect information games, including Chess and Go, combines planning and deep reinforcement learning with self-play. We extend this approach to imperfect information games and present ExIt-OOS, a novel approach to playing imperfect information games within the Expert Iteration framework and inspired by AlphaZero. We use Online Outcome Sampling, an online search algorithm for imperfect information games in place of MCTS. While training online, our neural strategy is used to improve the accuracy of playouts in OOS, allowing a learning and planning feedback loop for imperfect information games.
Tasks
Published	2018-08-30
URL	http://arxiv.org/abs/1808.10120v2
PDF	http://arxiv.org/pdf/1808.10120v2.pdf
PWC	https://paperswithcode.com/paper/exit-oos-towards-learning-from-planning-in
Repo	https://github.com/IAARhub/TrucoAnalytics
Framework	none

Communication Algorithms via Deep Learning


Title	Communication Algorithms via Deep Learning
Authors	Hyeji Kim, Yihan Jiang, Ranvir Rana, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
Abstract	Coding theory is a central discipline underpinning wireline and wireless modems that are the workhorses of the information age. Progress in coding theory is largely driven by individual human ingenuity with sporadic breakthroughs over the past century. In this paper we study whether it is possible to automate the discovery of decoding algorithms via deep learning. We study a family of sequential codes parameterized by recurrent neural network (RNN) architectures. We show that creatively designed and trained RNN architectures can decode well known sequential codes such as the convolutional and turbo codes with close to optimal performance on the additive white Gaussian noise (AWGN) channel, which itself is achieved by breakthrough algorithms of our times (Viterbi and BCJR decoders, representing dynamic programing and forward-backward algorithms). We show strong generalizations, i.e., we train at a specific signal to noise ratio and block length but test at a wide range of these quantities, as well as robustness and adaptivity to deviations from the AWGN setting.
Tasks
Published	2018-05-23
URL	http://arxiv.org/abs/1805.09317v1
PDF	http://arxiv.org/pdf/1805.09317v1.pdf
PWC	https://paperswithcode.com/paper/communication-algorithms-via-deep-learning
Repo	https://github.com/datlife/deepcom
Framework	tf

A Full End-to-End Semantic Role Labeler, Syntax-agnostic Over Syntax-aware?


Title	A Full End-to-End Semantic Role Labeler, Syntax-agnostic Over Syntax-aware?
Authors	Jiaxun Cai, Shexia He, Zuchao Li, Hai Zhao
Abstract	Semantic role labeling (SRL) is to recognize the predicate-argument structure of a sentence, including subtasks of predicate disambiguation and argument labeling. Previous studies usually formulate the entire SRL problem into two or more subtasks. For the first time, this paper introduces an end-to-end neural model which unifiedly tackles the predicate disambiguation and the argument labeling in one shot. Using a biaffine scorer, our model directly predicts all semantic role labels for all given word pairs in the sentence without relying on any syntactic parse information. Specifically, we augment the BiLSTM encoder with a non-linear transformation to further distinguish the predicate and the argument in a given sentence, and model the semantic role labeling process as a word pair classification task by employing the biaffine attentional mechanism. Though the proposed model is syntax-agnostic with local decoder, it outperforms the state-of-the-art syntax-aware SRL systems on the CoNLL-2008, 2009 benchmarks for both English and Chinese. To our best knowledge, we report the first syntax-agnostic SRL model that surpasses all known syntax-aware models.
Tasks	Semantic Role Labeling
Published	2018-08-11
URL	http://arxiv.org/abs/1808.03815v2
PDF	http://arxiv.org/pdf/1808.03815v2.pdf
PWC	https://paperswithcode.com/paper/a-full-end-to-end-semantic-role-labeler-1
Repo	https://github.com/JiaxunCai/Dynet-Biaffine-SRL
Framework	none

Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling


Title	Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling
Authors	Luheng He, Kenton Lee, Omer Levy, Luke Zettlemoyer
Abstract	Recent BIO-tagging-based neural semantic role labeling models are very high performing, but assume gold predicates as part of the input and cannot incorporate span-level features. We propose an end-to-end approach for jointly predicting all predicates, arguments spans, and the relations between them. The model makes independent decisions about what relationship, if any, holds between every possible word-span pair, and learns contextualized span representations that provide rich, shared input features for each decision. Experiments demonstrate that this approach sets a new state of the art on PropBank SRL without gold predicates.
Tasks	Semantic Role Labeling
Published	2018-05-12
URL	http://arxiv.org/abs/1805.04787v2
PDF	http://arxiv.org/pdf/1805.04787v2.pdf
PWC	https://paperswithcode.com/paper/jointly-predicting-predicates-and-arguments
Repo	https://github.com/luheng/lsgn
Framework	tf

GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training


Title	GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training
Authors	Samet Akcay, Amir Atapour-Abarghouei, Toby P. Breckon
Abstract	Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class (abnormal). While this can be addressed as a supervised learning problem, a significantly more challenging problem is that of detecting the unknown/unseen anomaly case that takes us instead into the space of a one-class, semi-supervised learning paradigm. We introduce such a novel anomaly detection model, by using a conditional generative adversarial network that jointly learns the generation of high-dimensional image space and the inference of latent space. Employing encoder-decoder-encoder sub-networks in the generator network enables the model to map the input image to a lower dimension vector, which is then used to reconstruct the generated output image. The use of the additional encoder network maps this generated image to its latent representation. Minimizing the distance between these images and the latent vectors during training aids in learning the data distribution for the normal samples. As a result, a larger distance metric from this learned data distribution at inference time is indicative of an outlier from that distribution - an anomaly. Experimentation over several benchmark datasets, from varying domains, shows the model efficacy and superiority over previous state-of-the-art approaches.
Tasks	Anomaly Detection
Published	2018-05-17
URL	http://arxiv.org/abs/1805.06725v3
PDF	http://arxiv.org/pdf/1805.06725v3.pdf
PWC	https://paperswithcode.com/paper/ganomaly-semi-supervised-anomaly-detection
Repo	https://github.com/lzwhard/ganomaly
Framework	pytorch

A Local Block Coordinate Descent Algorithm for the Convolutional Sparse Coding Model


Title	A Local Block Coordinate Descent Algorithm for the Convolutional Sparse Coding Model
Authors	Ev Zisselman, Jeremias Sulam, Michael Elad
Abstract	The Convolutional Sparse Coding (CSC) model has recently gained considerable traction in the signal and image processing communities. By providing a global, yet tractable, model that operates on the whole image, the CSC was shown to overcome several limitations of the patch-based sparse model while achieving superior performance in various applications. Contemporary methods for pursuit and learning the CSC dictionary often rely on the Alternating Direction Method of Multipliers (ADMM) in the Fourier domain for the computational convenience of convolutions, while ignoring the local characterizations of the image. A recent work by Papyan et al. suggested the SBDL algorithm for the CSC, while operating locally on image patches. SBDL demonstrates better performance compared to the Fourier-based methods, albeit still relying on the ADMM. In this work we maintain the localized strategy of the SBDL, while proposing a new and much simpler approach based on the Block Coordinate Descent algorithm - this method is termed Local Block Coordinate Descent (LoBCoD). Furthermore, we introduce a novel stochastic gradient descent version of LoBCoD for training the convolutional filters. The Stochastic-LoBCoD leverages the benefits of online learning, while being applicable to a single training image. We demonstrate the advantages of the proposed algorithms for image inpainting and multi-focus image fusion, achieving state-of-the-art results.
Tasks	Image Inpainting
Published	2018-11-01
URL	http://arxiv.org/abs/1811.00312v1
PDF	http://arxiv.org/pdf/1811.00312v1.pdf
PWC	https://paperswithcode.com/paper/a-local-block-coordinate-descent-algorithm
Repo	https://github.com/EvZissel/LoBCoD
Framework	none

Local angles and dimension estimation from data on manifolds


Title	Local angles and dimension estimation from data on manifolds
Authors	Mateo Díaz, Adolfo J. Quiroz, Mauricio Velasco
Abstract	For data living in a manifold $M\subseteq \mathbb{R}^m$ and a point $p\in M$ we consider a statistic $U_{k,n}$ which estimates the variance of the angle between pairs of vectors $X_i-p$ and $X_j-p$, for data points $X_i$, $X_j$, near $p$, and evaluate this statistic as a tool for estimation of the intrinsic dimension of $M$ at $p$. Consistency of the local dimension estimator is established and the asymptotic distribution of $U_{k,n}$ is found under minimal regularity assumptions. Performance of the proposed methodology is compared against state-of-the-art methods on simulated data.
Tasks
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01577v1
PDF	http://arxiv.org/pdf/1805.01577v1.pdf
PWC	https://paperswithcode.com/paper/local-angles-and-dimension-estimation-from
Repo	https://github.com/mateodd25/ANOVA_dimension_estimator
Framework	none

Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study


Title	Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study
Authors	Zhenyu Wu, Zhangyang Wang, Zhaowen Wang, Hailin Jin
Abstract	This paper aims to improve privacy-preserving visual recognition, an increasingly demanded feature in smart camera applications, by formulating a unique adversarial training framework. The proposed framework explicitly learns a degradation transform for the original video inputs, in order to optimize the trade-off between target task performance and the associated privacy budgets on the degraded video. A notable challenge is that the privacy budget, often defined and measured in task-driven contexts, cannot be reliably indicated using any single model performance, because a strong protection of privacy has to sustain against any possible model that tries to hack privacy information. Such an uncommon situation has motivated us to propose two strategies, i.e., budget model restarting and ensemble, to enhance the generalization of the learned degradation on protecting privacy against unseen hacker models. Novel training strategies, evaluation protocols, and result visualization methods have been designed accordingly. Two experiments on privacy-preserving action recognition, with privacy budgets defined in various ways, manifest the compelling effectiveness of the proposed framework in simultaneously maintaining high target task (action recognition) performance while suppressing the privacy breach risk.
Tasks	Temporal Action Localization
Published	2018-07-22
URL	http://arxiv.org/abs/1807.08379v1
PDF	http://arxiv.org/pdf/1807.08379v1.pdf
PWC	https://paperswithcode.com/paper/towards-privacy-preserving-visual-recognition
Repo	https://github.com/TAMU-VITA/Privacy-AdversarialLearning
Framework	tf

Gibson Env: Real-World Perception for Embodied Agents


Title	Gibson Env: Real-World Perception for Embodied Agents
Authors	Fei Xia, Amir Zamir, Zhi-Yang He, Alexander Sax, Jitendra Malik, Silvio Savarese
Abstract	Developing visual perception models for active agents and sensorimotor control are cumbersome to be done in the physical world, as existing algorithms are too slow to efficiently learn in real-time and robots are fragile and costly. This has given rise to learning-in-simulation which consequently casts a question on whether the results transfer to real-world. In this paper, we are concerned with the problem of developing real-world perception for active agents, propose Gibson Virtual Environment for this purpose, and showcase sample perceptual tasks learned therein. Gibson is based on virtualizing real spaces, rather than using artificially designed ones, and currently includes over 1400 floor spaces from 572 full buildings. The main characteristics of Gibson are: I. being from the real-world and reflecting its semantic complexity, II. having an internal synthesis mechanism, “Goggles”, enabling deploying the trained models in real-world without needing further domain adaptation, III. embodiment of agents and making them subject to constraints of physics and space.
Tasks	Domain Adaptation
Published	2018-08-31
URL	http://arxiv.org/abs/1808.10654v1
PDF	http://arxiv.org/pdf/1808.10654v1.pdf
PWC	https://paperswithcode.com/paper/gibson-env-real-world-perception-for-embodied
Repo	https://github.com/StanfordVL/GibsonSim2RealCallenge
Framework	tf

Video Based Reconstruction of 3D People Models


Title	Video Based Reconstruction of 3D People Models
Authors	Thiemo Alldieck, Marcus Magnor, Weipeng Xu, Christian Theobalt, Gerard Pons-Moll
Abstract	This paper describes how to obtain accurate 3D body models and texture of arbitrary people from a single, monocular video in which a person is moving. Based on a parametric body model, we present a robust processing pipeline achieving 3D model fits with 5mm accuracy also for clothed people. Our main contribution is a method to nonrigidly deform the silhouette cones corresponding to the dynamic human silhouettes, resulting in a visual hull in a common reference frame that enables surface reconstruction. This enables efficient estimation of a consensus 3D shape, texture and implanted animation skeleton based on a large number of frames. We present evaluation results for a number of test subjects and analyze overall performance. Requiring only a smartphone or webcam, our method enables everyone to create their own fully animatable digital double, e.g., for social VR applications or virtual try-on for online fashion shopping.
Tasks
Published	2018-03-13
URL	http://arxiv.org/abs/1803.04758v3
PDF	http://arxiv.org/pdf/1803.04758v3.pdf
PWC	https://paperswithcode.com/paper/video-based-reconstruction-of-3d-people
Repo	https://github.com/thmoa/videoavatars
Framework	none

Random deep neural networks are biased towards simple functions


Title	Random deep neural networks are biased towards simple functions
Authors	Giacomo De Palma, Bobak Toussi Kiani, Seth Lloyd
Abstract	We prove that the binary classifiers of bit strings generated by random wide deep neural networks with ReLU activation function are biased towards simple functions. The simplicity is captured by the following two properties. For any given input bit string, the average Hamming distance of the closest input bit string with a different classification is at least sqrt(n / (2{\pi} log n)), where n is the length of the string. Moreover, if the bits of the initial string are flipped randomly, the average number of flips required to change the classification grows linearly with n. These results are confirmed by numerical experiments on deep neural networks with two hidden layers, and settle the conjecture stating that random deep neural networks are biased towards simple functions. This conjecture was proposed and numerically explored in [Valle P'erez et al., ICLR 2019] to explain the unreasonably good generalization properties of deep learning algorithms. The probability distribution of the functions generated by random deep neural networks is a good choice for the prior probability distribution in the PAC-Bayesian generalization bounds. Our results constitute a fundamental step forward in the characterization of this distribution, therefore contributing to the understanding of the generalization properties of deep learning algorithms.
Tasks
Published	2018-12-25
URL	https://arxiv.org/abs/1812.10156v2
PDF	https://arxiv.org/pdf/1812.10156v2.pdf
PWC	https://paperswithcode.com/paper/deep-neural-networks-are-biased-towards
Repo	https://github.com/bkiani/random_NN_simplicity
Framework	tf

Convolutional Neural Networks with Alternately Updated Clique


Title	Convolutional Neural Networks with Alternately Updated Clique
Authors	Yibo Yang, Zhisheng Zhong, Tiancheng Shen, Zhouchen Lin
Abstract	Improving information flow in deep networks helps to ease the training difficulties and utilize parameters more efficiently. Here we propose a new convolutional neural network architecture with alternately updated clique (CliqueNet). In contrast to prior networks, there are both forward and backward connections between any two layers in the same block. The layers are constructed as a loop and are updated alternately. The CliqueNet has some unique properties. For each layer, it is both the input and output of any other layer in the same block, so that the information flow among layers is maximized. During propagation, the newly updated layers are concatenated to re-update previously updated layer, and parameters are reused for multiple times. This recurrent feedback structure is able to bring higher level visual information back to refine low-level filters and achieve spatial attention. We analyze the features generated at different stages and observe that using refined features leads to a better result. We adopt a multi-scale feature strategy that effectively avoids the progressive growth of parameters. Experiments on image recognition datasets including CIFAR-10, CIFAR-100, SVHN and ImageNet show that our proposed models achieve the state-of-the-art performance with fewer parameters.
Tasks
Published	2018-02-28
URL	http://arxiv.org/abs/1802.10419v3
PDF	http://arxiv.org/pdf/1802.10419v3.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-networks-with-1
Repo	https://github.com/yaowenlong/clique
Framework	pytorch

Image Inspired Poetry Generation in XiaoIce


Title	Image Inspired Poetry Generation in XiaoIce
Authors	Wen-Feng Cheng, Chao-Chung Wu, Ruihua Song, Jianlong Fu, Xing Xie, Jian-Yun Nie
Abstract	Vision is a common source of inspiration for poetry. The objects and the sentimental imprints that one perceives from an image may lead to various feelings depending on the reader. In this paper, we present a system of poetry generation from images to mimic the process. Given an image, we first extract a few keywords representing objects and sentiments perceived from the image. These keywords are then expanded to related ones based on their associations in human written poems. Finally, verses are generated gradually from the keywords using recurrent neural networks trained on existing poems. Our approach is evaluated by human assessors and compared to other generation baselines. The results show that our method can generate poems that are more artistic than the baseline methods. This is one of the few attempts to generate poetry from images. By deploying our proposed approach, XiaoIce has already generated more than 12 million poems for users since its release in July 2017. A book of its poems has been published by Cheers Publishing, which claimed that the book is the first-ever poetry collection written by an AI in human history.
Tasks
Published	2018-08-09
URL	http://arxiv.org/abs/1808.03090v1
PDF	http://arxiv.org/pdf/1808.03090v1.pdf
PWC	https://paperswithcode.com/paper/image-inspired-poetry-generation-in-xiaoice
Repo	https://github.com/forrestbing/chinese-poetry-generation
Framework	none