October 15, 2019

2823 words 14 mins read

Paper Group NANR 243

Recognize Actions by Disentangling Components of Dynamics. Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction. Trojan Horses in Amazon’s Castle: Understanding the Incentivized Online Reviews. Fluid Annotation: A Granularity-aware Annotation Tool for Chinese Word Fluidity. One Kernel to Solve Nearly Everything: Unified …

Recognize Actions by Disentangling Components of Dynamics


Title	Recognize Actions by Disentangling Components of Dynamics
Authors	Yue Zhao, Yuanjun Xiong, Dahua Lin
Abstract	Despite the remarkable progress in action recognition over the past several years, existing methods remain limited in efficiency and effectiveness. The methods treating appearance and motion as separate streams are usually subject to the cost of optical flow computation, while those relying on 3D convolution on the original video frames often yield inferior performance in practice. In this paper, we propose a new ConvNet architecture for video representation learning, which can derive disentangled components of dynamics purely from raw video frames, without the need of optical flow estimation. Particularly, the learned representation comprises three components for representing static appearance, apparent motion, and appearance changes. We introduce 3D pooling, cost volume processing, and warped feature differences, respectively for extracting the three components above. These modules are incorporated as three branches in our unified network, which share the underlying features and are learned jointly in an end-to-end manner. On two large datasets UCF101 and Kinetics our method obtained competitive performances with high efficiency, using only the RGB frame sequence as input.
Tasks	Optical Flow Estimation, Representation Learning, Temporal Action Localization
Published	2018-06-01
URL	http://openaccess.thecvf.com/content_cvpr_2018/html/Zhao_Recognize_Actions_by_CVPR_2018_paper.html
PDF	http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhao_Recognize_Actions_by_CVPR_2018_paper.pdf
PWC	https://paperswithcode.com/paper/recognize-actions-by-disentangling-components
Repo
Framework

Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction


Title	Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction
Authors	Kevin Ellis, Lucas Morales, Mathias Sablé-Meyer, Armando Solar-Lezama, Josh Tenenbaum
Abstract	Successful approaches to program induction require a hand-engineered domain-specific language (DSL), constraining the space of allowed programs and imparting prior knowledge of the domain. We contribute a program induction algorithm that learns a DSL while jointly training a neural network to efficiently search for programs in the learned DSL. We use our model to synthesize functions on lists, edit text, and solve symbolic regression problems, showing how the model learns a domain-specific library of program components for expressing solutions to problems in the domain.
Tasks
Published	2018-12-01
URL	http://papers.nips.cc/paper/8006-learning-libraries-of-subroutines-for-neurallyguided-bayesian-program-induction
PDF	http://papers.nips.cc/paper/8006-learning-libraries-of-subroutines-for-neurallyguided-bayesian-program-induction.pdf
PWC	https://paperswithcode.com/paper/learning-libraries-of-subroutines-for
Repo
Framework

Trojan Horses in Amazon’s Castle: Understanding the Incentivized Online Reviews


Title	Trojan Horses in Amazon’s Castle: Understanding the Incentivized Online Reviews
Authors	S Jamshidi, R Rejaie, J Li
Abstract	During the past few years, sellers have increasingly offered discounted or free products to selected reviewers of e-commerce platforms in exchange for their reviews. Such incentivized (and often very positive) reviews can improve the rating of a product which in turn sways other users’ opinions about the product. Despite their importance, the prevalence, characteristics, and the influence of incentivized reviews in a major e-commerce platform have not been systematically and quantitatively studied. This paper examines the problem of detecting and characterizing incentivized reviews in two primary categories of Amazon products. We describe a new method to identify Explicitly Incentivized Reviews (EIRs) and then collect a few datasets to capture an extensive collection of EIRs along with their associated products and reviewers. We show that the key features of EIRs and normal reviews exhibit different …
Tasks
Published	2018-06-06
URL	http://soja.me/papers/SOJA_ICWSM_Amazon_Project.pdf
PDF	http://soja.me/papers/SOJA_ICWSM_Amazon_Project.pdf
PWC	https://paperswithcode.com/paper/trojan-horses-in-amazons-castle-understanding
Repo
Framework

Fluid Annotation: A Granularity-aware Annotation Tool for Chinese Word Fluidity


Title	Fluid Annotation: A Granularity-aware Annotation Tool for Chinese Word Fluidity
Authors	Shu-Kai Hsieh, Yu-Hsiang Tseng, Chih-Yao Lee, Chiung-Yu Chiang
Abstract
Tasks	Chinese Word Segmentation, Domain Adaptation
Published	2018-05-01
URL	https://www.aclweb.org/anthology/L18-1207/
PDF	https://www.aclweb.org/anthology/L18-1207
PWC	https://paperswithcode.com/paper/fluid-annotation-a-granularity-aware
Repo
Framework

One Kernel to Solve Nearly Everything: Unified 3D Binary Convolutions for Image Analysis


Title	One Kernel to Solve Nearly Everything: Unified 3D Binary Convolutions for Image Analysis
Authors	MP Heinrich, O Oktay, N Bouteldja
Abstract	Deep networks have set the state-of-the-art in most image analysis tasks by replacing handcrafted features with learned convolution filters within end-to-end trainable architectures. Still, the specifications of a convolutional network are subject to much manual design - the shape and size of the receptive field for convolutional operations is a very sensitive part that has to be tuned for different image analysis applications. 3D fully-convolutional multi-scale architectures with skip-connection that excel at semantic segmentation and landmark localisation have huge memory requirements and rely on large annotated datasets - an important limitation for wider adaptation in medical image analysis. We propose a novel and effective method based on a single trainable 3D convolution kernel that addresses these issues and enables high quality results with a compact four-layer architecture and without sensitive hyperparameters for convolutions and architectural design. Instead of a manual choice of filter size, dilation of weights, and number of scales, our one binary extremely large and inflecting sparse kernel (OBELISK) automatically learns filter offsets in a differentiable continuous space together with weight coefficients. Geometric data augmentation can be directly incorporated into the training by simple coordinate transforms. This powerful new architecture has less than 130’000 parameters, can be trained in few minutes with only 700 MBytes of memory and achieves an increase of Dice overlap of +5.5% compared to the U-Net for CT multi-organ segmentation.
Tasks	Data Augmentation, Semantic Segmentation
Published	2018-04-11
URL	https://vitalab.github.io/deep-learning/2018/11/23/OBELISK.html
PDF	https://openreview.net/pdf?id=BkZu9wooz
PWC	https://paperswithcode.com/paper/one-kernel-to-solve-nearly-everything-unified
Repo
Framework

Variational Inference and Model Selection with Generalized Evidence Bounds


Title	Variational Inference and Model Selection with Generalized Evidence Bounds
Authors	Liqun Chen, Chenyang Tao, Ruiyi Zhang, Ricardo Henao, Lawrence Carin Duke
Abstract	Recent advances on the scalability and flexibility of variational inference have made it successful at unravelling hidden patterns in complex data. In this work we propose a new variational bound formulation, yielding an estimator that extends beyond the conventional variational bound. It naturally subsumes the importance-weighted and Renyi bounds as special cases, and it is provably sharper than these counterparts. We also present an improved estimator for variational learning, and advocate a novel high signal-to-variance ratio update rule for the variational parameters. We discuss model-selection issues associated with existing evidence-lower-bound-based variational inference procedures, and show how to leverage the flexibility of our new formulation to address them. Empirical evidence is provided to validate our claims.
Tasks	Model Selection
Published	2018-07-01
URL	https://icml.cc/Conferences/2018/Schedule?showEvent=2377
PDF	http://proceedings.mlr.press/v80/chen18k/chen18k.pdf
PWC	https://paperswithcode.com/paper/variational-inference-and-model-selection
Repo
Framework

Stochastic PCA with $\ell_2$ and $\ell_1$ Regularization


Title	Stochastic PCA with $\ell_2$ and $\ell_1$ Regularization
Authors	Poorya Mianjy, Raman Arora
Abstract	We revisit convex relaxation based methods for stochastic optimization of principal component analysis (PCA). While methods that directly solve the nonconvex problem have been shown to be optimal in terms of statistical and computational efficiency, the methods based on convex relaxation have been shown to enjoy comparable, or even superior, empirical performance – this motivates the need for a deeper formal understanding of the latter. Therefore, in this paper, we study variants of stochastic gradient descent for a convex relaxation of PCA with (a) $\ell_2$, (b) $\ell_1$, and (c) elastic net ($\ell_1+\ell_2)$ regularization in the hope that these variants yield (a) better iteration complexity, (b) better control on the rank of the intermediate iterates, and (c) both, respectively. We show, theoretically and empirically, that compared to previous work on convex relaxation based methods, the proposed variants yield faster convergence and improve overall runtime to achieve a certain user-specified $\epsilon$-suboptimality on the PCA objective. Furthermore, the proposed methods are shown to converge both in terms of the PCA objective as well as the distance between subspaces. However, there still remains a gap in computational requirements for the proposed methods when compared with existing nonconvex approaches.
Tasks	Stochastic Optimization
Published	2018-07-01
URL	https://icml.cc/Conferences/2018/Schedule?showEvent=2479
PDF	http://proceedings.mlr.press/v80/mianjy18a/mianjy18a.pdf
PWC	https://paperswithcode.com/paper/stochastic-pca-with-ell_2-and-ell_1
Repo
Framework

ECGNET: Learning Where to Attend for Detection of Atrial Fibrillation with Deep Visual Attention


Title	ECGNET: Learning Where to Attend for Detection of Atrial Fibrillation with Deep Visual Attention
Authors	Sajad Mousavi, Fatemeh Afghah, Abolfazl Razi, U. Rajendra Acharya
Abstract	The complexity of the patterns associated with Atrial Fibrillation (AF) and the high level of noise affecting these patterns have significantly limited the current signal processing and shallow machine learning approaches to get accurate AF detection results. Deep neural networks have shown to be very powerful to learn the non-linear patterns in the data. While a deep learning approach attempts to learn complex pattern related to the presence of AF in the ECG, they can benefit from knowing which parts of the signal is more important to focus during learning. In this paper, we introduce a two-channel deep neural network to more accurately detect AF presented in the ECG signal. The first channel takes in a preprocessed ECG signal and automatically learns where to attend for detection of AF. The second channel simultaneously takes in the preprocessed ECG signal to consider all features of entire signals. The model shows via visualization that what parts of the given ECG signal are important to attend while trying to detect atrial fibrillation. In addition, this combination significantly improves the performance of the atrial fibrillation detection (achieved a sensitivity of 99.53%, specificity of 99.26% and accuracy of 99.40% on the MIT-BIH atrial fibrillation database with 5-s ECG segments.)
Tasks	Arrhythmia Detection, Atrial Fibrillation Detection, Electrocardiography (ECG)
Published	2018-12-09
URL	https://arxiv.org/abs/1812.07422
PDF	https://arxiv.org/pdf/1812.07422
PWC	https://paperswithcode.com/paper/ecgnet-learning-where-to-attend-for-detection
Repo
Framework

Monte-Carlo Tree Search for Constrained POMDPs


Title	Monte-Carlo Tree Search for Constrained POMDPs
Authors	Jongmin Lee, Geon-Hyeong Kim, Pascal Poupart, Kee-Eung Kim
Abstract	Monte-Carlo Tree Search (MCTS) has been successfully applied to very large POMDPs, a standard model for stochastic sequential decision-making problems. However, many real-world problems inherently have multiple goals, where multi-objective formulations are more natural. The constrained POMDP (CPOMDP) is such a model that maximizes the reward while constraining the cost, extending the standard POMDP model. To date, solution methods for CPOMDPs assume an explicit model of the environment, and thus are hardly applicable to large-scale real-world problems. In this paper, we present CC-POMCP (Cost-Constrained POMCP), an online MCTS algorithm for large CPOMDPs that leverages the optimization of LP-induced parameters and only requires a black-box simulator of the environment. In the experiments, we demonstrate that CC-POMCP converges to the optimal stochastic action selection in CPOMDP and pushes the state-of-the-art by being able to scale to very large problems.
Tasks	Decision Making
Published	2018-12-01
URL	http://papers.nips.cc/paper/8017-monte-carlo-tree-search-for-constrained-pomdps
PDF	http://papers.nips.cc/paper/8017-monte-carlo-tree-search-for-constrained-pomdps.pdf
PWC	https://paperswithcode.com/paper/monte-carlo-tree-search-for-constrained
Repo
Framework

Dropout Training, Data-dependent Regularization, and Generalization Bounds


Title	Dropout Training, Data-dependent Regularization, and Generalization Bounds
Authors	Wenlong Mou, Yuchen Zhou, Jun Gao, Liwei Wang
Abstract	We study the problem of generalization guarantees for dropout training. A general framework is first proposed for learning procedures with random perturbation on model parameters. The generalization error is bounded by sum of two offset Rademacher complexities: the main term is Rademacher complexity of the hypothesis class with minus offset induced by the perturbation variance, which characterizes data-dependent regularization by the random perturbation; the auxiliary term is offset Rademacher complexity for the variance class, controlling the degree to which this regularization effect can be weakened. For neural networks, we estimate upper and lower bounds for the variance induced by truthful dropout, a variant of dropout that we propose to ensure unbiased output and fit into our framework, and the variance bounds exhibits connection to adaptive regularization methods. By applying our framework to ReLU networks with one hidden layer, a generalization upper bound is derived with no assumptions on the parameter norms or data distribution, with $O(1/n)$ fast rate and adaptivity to geometry of data points being achieved at the same time.
Tasks
Published	2018-07-01
URL	https://icml.cc/Conferences/2018/Schedule?showEvent=2000
PDF	http://proceedings.mlr.press/v80/mou18a/mou18a.pdf
PWC	https://paperswithcode.com/paper/dropout-training-data-dependent
Repo
Framework

Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation


Title	Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation
Authors	Tianyu He, Xu Tan, Yingce Xia, Di He, Tao Qin, Zhibo Chen, Tie-Yan Liu
Abstract	Neural Machine Translation (NMT) has achieved remarkable progress with the quick evolvement of model structures. In this paper, we propose the concept of layer-wise coordination for NMT, which explicitly coordinates the learning of hidden representations of the encoder and decoder together layer by layer, gradually from low level to high level. Specifically, we design a layer-wise attention and mixed attention mechanism, and further share the parameters of each layer between the encoder and decoder to regularize and coordinate the learning. Experiments show that combined with the state-of-the-art Transformer model, layer-wise coordination achieves improvements on three IWSLT and two WMT translation tasks. More specifically, our method achieves 34.43 and 29.01 BLEU score on WMT16 English-Romanian and WMT14 English-German tasks, outperforming the Transformer baseline.
Tasks	Machine Translation
Published	2018-12-01
URL	http://papers.nips.cc/paper/8019-layer-wise-coordination-between-encoder-and-decoder-for-neural-machine-translation
PDF	http://papers.nips.cc/paper/8019-layer-wise-coordination-between-encoder-and-decoder-for-neural-machine-translation.pdf
PWC	https://paperswithcode.com/paper/layer-wise-coordination-between-encoder-and
Repo
Framework

Learning Diffusion using Hyperparameters


Title	Learning Diffusion using Hyperparameters
Authors	Dimitris Kalimeris, Yaron Singer, Karthik Subbian, Udi Weinsberg
Abstract	In this paper we advocate for a hyperparametric approach to learn diffusion in the independent cascade (IC) model. The sample complexity of this model is a function of the number of edges in the network and consequently learning becomes infeasible when the network is large. We study a natural restriction of the hypothesis class using additional information available in order to dramatically reduce the sample complexity of the learning process. In particular we assume that diffusion probabilities can be described as a function of a global hyperparameter and features of the individuals in the network. One of the main challenges with this approach is that training a model reduces to optimizing a non-convex objective. Despite this obstacle, we can shrink the best-known sample complexity bound for learning IC by a factor of E/d where E is the number of edges in the graph and d is the dimension of the hyperparameter. We show that under mild assumptions about the distribution generating the samples one can provably train a model with low generalization error. Finally, we use large-scale diffusion data from Facebook to show that a hyperparametric model using approximately 20 features per node achieves remarkably high accuracy.
Tasks
Published	2018-07-01
URL	https://icml.cc/Conferences/2018/Schedule?showEvent=1880
PDF	http://proceedings.mlr.press/v80/kalimeris18a/kalimeris18a.pdf
PWC	https://paperswithcode.com/paper/learning-diffusion-using-hyperparameters
Repo
Framework

Decoupling Gradient-Like Learning Rules from Representations


Title	Decoupling Gradient-Like Learning Rules from Representations
Authors	Philip Thomas, Christoph Dann, Emma Brunskill
Abstract	In machine learning, learning often corresponds to changing the parameters of a parameterized function. A learning rule is an algorithm or mathematical expression that specifies precisely how the parameters should be changed. When creating a machine learning system, we must make two decisions: what representation should be used (i.e., what parameterized function should be used) and what learning rule should be used to search through the resulting set of representable functions. In this paper we focus on gradient-like learning rules, wherein these two decisions are coupled in a subtle (and often unintentional) way. Using most learning rules, these two decisions are coupled in a subtle (and often unintentional) way. That is, using the same learning rule with two different representations that can represent the same sets of functions can result in two different outcomes. After arguing that this coupling is undesirable, particularly when using neural networks, we present a method for partially decoupling these two decisions for a broad class of gradient-like learning rules that span unsupervised learning, reinforcement learning, and supervised learning.
Tasks
Published	2018-07-01
URL	https://icml.cc/Conferences/2018/Schedule?showEvent=2343
PDF	http://proceedings.mlr.press/v80/thomas18a/thomas18a.pdf
PWC	https://paperswithcode.com/paper/decoupling-gradient-like-learning-rules-from
Repo
Framework

Semi-Supervised Lexicon Learning for Wide-Coverage Semantic Parsing


Title	Semi-Supervised Lexicon Learning for Wide-Coverage Semantic Parsing
Authors	Bo Chen, Bo An, Le Sun, Xianpei Han
Abstract	Semantic parsers critically rely on accurate and high-coverage lexicons. However, traditional semantic parsers usually utilize annotated logical forms to learn the lexicon, which often suffer from the lexicon coverage problem. In this paper, we propose a graph-based semi-supervised learning framework that makes use of large text corpora and lexical resources. This framework first constructs a graph with a phrase similarity model learned by utilizing many text corpora and lexical resources. Next, graph propagation algorithm identifies the label distribution of unlabeled phrases from labeled ones. We evaluate our approach on two benchmarks: Webquestions and Free917. The results show that, in both datasets, our method achieves substantial improvement when comparing to the base system that does not utilize the learned lexicon, and gains competitive results when comparing to state-of-the-art systems.
Tasks	Semantic Parsing
Published	2018-08-01
URL	https://www.aclweb.org/anthology/C18-1076/
PDF	https://www.aclweb.org/anthology/C18-1076
PWC	https://paperswithcode.com/paper/semi-supervised-lexicon-learning-for-wide
Repo
Framework

Crowdsourcing with Arbitrary Adversaries


Title	Crowdsourcing with Arbitrary Adversaries
Authors	Matthaeus Kleindessner, Pranjal Awasthi
Abstract	Most existing works on crowdsourcing assume that the workers follow the Dawid-Skene model, or the one-coin model as its special case, where every worker makes mistakes independently of other workers and with the same error probability for every task. We study a significant extension of this restricted model. We allow almost half of the workers to deviate from the one-coin model and for those workers, their probabilities of making an error to be task-dependent and to be arbitrarily correlated. In other words, we allow for arbitrary adversaries, for which not only error probabilities can be high, but which can also perfectly collude. In this adversarial scenario, we design an efficient algorithm to consistently estimate the workers’ error probabilities.
Tasks
Published	2018-07-01
URL	https://icml.cc/Conferences/2018/Schedule?showEvent=2054
PDF	http://proceedings.mlr.press/v80/kleindessner18a/kleindessner18a.pdf
PWC	https://paperswithcode.com/paper/crowdsourcing-with-arbitrary-adversaries
Repo
Framework