October 21, 2019

2813 words 14 mins read

Paper Group AWR 138

Differentially Private Releasing via Deep Generative Model (Technical Report). DRCD: a Chinese Machine Reading Comprehension Dataset. Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods. Density Adaptive Point Set Registration. MIXGAN: Learning Concepts from Different Domains for M …

Differentially Private Releasing via Deep Generative Model (Technical Report)


Title	Differentially Private Releasing via Deep Generative Model (Technical Report)
Authors	Xinyang Zhang, Shouling Ji, Ting Wang
Abstract	Privacy-preserving releasing of complex data (e.g., image, text, audio) represents a long-standing challenge for the data mining research community. Due to rich semantics of the data and lack of a priori knowledge about the analysis task, excessive sanitization is often necessary to ensure privacy, leading to significant loss of the data utility. In this paper, we present dp-GAN, a general private releasing framework for semantic-rich data. Instead of sanitizing and then releasing the data, the data curator publishes a deep generative model which is trained using the original data in a differentially private manner; with the generative model, the analyst is able to produce an unlimited amount of synthetic data for arbitrary analysis tasks. In contrast of alternative solutions, dp-GAN highlights a set of key features: (i) it provides theoretical privacy guarantee via enforcing the differential privacy principle; (ii) it retains desirable utility in the released model, enabling a variety of otherwise impossible analyses; and (iii) most importantly, it achieves practical training scalability and stability by employing multi-fold optimization strategies. Through extensive empirical evaluation on benchmark datasets and analyses, we validate the efficacy of dp-GAN.
Tasks
Published	2018-01-05
URL	http://arxiv.org/abs/1801.01594v2
PDF	http://arxiv.org/pdf/1801.01594v2.pdf
PWC	https://paperswithcode.com/paper/differentially-private-releasing-via-deep
Repo	https://github.com/alexandrehuat/dp-gan
Framework	tf

DRCD: a Chinese Machine Reading Comprehension Dataset


Title	DRCD: a Chinese Machine Reading Comprehension Dataset
Authors	Chih Chieh Shao, Trois Liu, Yuting Lai, Yiying Tseng, Sam Tsai
Abstract	In this paper, we introduce DRCD (Delta Reading Comprehension Dataset), an open domain traditional Chinese machine reading comprehension (MRC) dataset. This dataset aimed to be a standard Chinese machine reading comprehension dataset, which can be a source dataset in transfer learning. The dataset contains 10,014 paragraphs from 2,108 Wikipedia articles and 30,000+ questions generated by annotators. We build a baseline model that achieves an F1 score of 89.59%. F1 score of Human performance is 93.30%.
Tasks	Machine Reading Comprehension, Reading Comprehension, Transfer Learning
Published	2018-06-04
URL	https://arxiv.org/abs/1806.00920v3
PDF	https://arxiv.org/pdf/1806.00920v3.pdf
PWC	https://paperswithcode.com/paper/drcd-a-chinese-machine-reading-comprehension
Repo	https://github.com/DRCSolutionService/DRCD
Framework	none

Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods


Title	Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods
Authors	Deirdre Quillen, Eric Jang, Ofir Nachum, Chelsea Finn, Julian Ibarz, Sergey Levine
Abstract	In this paper, we explore deep reinforcement learning algorithms for vision-based robotic grasping. Model-free deep reinforcement learning (RL) has been successfully applied to a range of challenging environments, but the proliferation of algorithms makes it difficult to discern which particular approach would be best suited for a rich, diverse task like grasping. To answer this question, we propose a simulated benchmark for robotic grasping that emphasizes off-policy learning and generalization to unseen objects. Off-policy learning enables utilization of grasping data over a wide variety of objects, and diversity is important to enable the method to generalize to new objects that were not seen during training. We evaluate the benchmark tasks against a variety of Q-function estimation methods, a method previously proposed for robotic grasping with deep neural network models, and a novel approach based on a combination of Monte Carlo return estimation and an off-policy correction. Our results indicate that several simple methods provide a surprisingly strong competitor to popular algorithms such as double Q-learning, and our analysis of stability sheds light on the relative tradeoffs between the algorithms.
Tasks	Q-Learning, Robotic Grasping
Published	2018-02-28
URL	http://arxiv.org/abs/1802.10264v2
PDF	http://arxiv.org/pdf/1802.10264v2.pdf
PWC	https://paperswithcode.com/paper/deep-reinforcement-learning-for-vision-based
Repo	https://github.com/mveres01/deepq-grasping
Framework	pytorch

Density Adaptive Point Set Registration


Title	Density Adaptive Point Set Registration
Authors	Felix Järemo Lawin, Martin Danelljan, Fahad Shahbaz Khan, Per-Erik Forssén, Michael Felsberg
Abstract	Probabilistic methods for point set registration have demonstrated competitive results in recent years. These techniques estimate a probability distribution model of the point clouds. While such a representation has shown promise, it is highly sensitive to variations in the density of 3D points. This fundamental problem is primarily caused by changes in the sensor location across point sets. We revisit the foundations of the probabilistic registration paradigm. Contrary to previous works, we model the underlying structure of the scene as a latent probability distribution, and thereby induce invariance to point set density changes. Both the probabilistic model of the scene and the registration parameters are inferred by minimizing the Kullback-Leibler divergence in an Expectation Maximization based framework. Our density-adaptive registration successfully handles severe density variations commonly encountered in terrestrial Lidar applications. We perform extensive experiments on several challenging real-world Lidar datasets. The results demonstrate that our approach outperforms state-of-the-art probabilistic methods for multi-view registration, without the need of re-sampling. Code is available at https://github.com/felja633/DARE.
Tasks
Published	2018-04-04
URL	http://arxiv.org/abs/1804.01495v2
PDF	http://arxiv.org/pdf/1804.01495v2.pdf
PWC	https://paperswithcode.com/paper/density-adaptive-point-set-registration
Repo	https://github.com/felja633/DARE
Framework	none

MIXGAN: Learning Concepts from Different Domains for Mixture Generation


Title	MIXGAN: Learning Concepts from Different Domains for Mixture Generation
Authors	Guang-Yuan Hao, Hong-Xing Yu, Wei-Shi Zheng
Abstract	In this work, we present an interesting attempt on mixture generation: absorbing different image concepts (e.g., content and style) from different domains and thus generating a new domain with learned concepts. In particular, we propose a mixture generative adversarial network (MIXGAN). MIXGAN learns concepts of content and style from two domains respectively, and thus can join them for mixture generation in a new domain, i.e., generating images with content from one domain and style from another. MIXGAN overcomes the limitation of current GAN-based models which either generate new images in the same domain as they observed in training stage, or require off-the-shelf content templates for transferring or translation. Extensive experimental results demonstrate the effectiveness of MIXGAN as compared to related state-of-the-art GAN-based models.
Tasks
Published	2018-07-04
URL	http://arxiv.org/abs/1807.01659v1
PDF	http://arxiv.org/pdf/1807.01659v1.pdf
PWC	https://paperswithcode.com/paper/mixgan-learning-concepts-from-different
Repo	https://github.com/GuangyuanHao/MIXGAN
Framework	tf

Learning Linear Transformations for Fast Arbitrary Style Transfer


Title	Learning Linear Transformations for Fast Arbitrary Style Transfer
Authors	Xueting Li, Sifei Liu, Jan Kautz, Ming-Hsuan Yang
Abstract	Given a random pair of images, an arbitrary style transfer method extracts the feel from the reference image to synthesize an output based on the look of the other content image. Recent arbitrary style transfer methods transfer second order statistics from reference image onto content image via a multiplication between content image features and a transformation matrix, which is computed from features with a pre-determined algorithm. These algorithms either require computationally expensive operations, or fail to model the feature covariance and produce artifacts in synthesized images. Generalized from these methods, in this work, we derive the form of transformation matrix theoretically and present an arbitrary style transfer approach that learns the transformation matrix with a feed-forward network. Our algorithm is highly efficient yet allows a flexible combination of multi-level styles while preserving content affinity during style transfer process. We demonstrate the effectiveness of our approach on four tasks: artistic style transfer, video and photo-realistic style transfer as well as domain adaptation, including comparisons with the state-of-the-art methods.
Tasks	Domain Adaptation, Style Transfer
Published	2018-08-14
URL	http://arxiv.org/abs/1808.04537v1
PDF	http://arxiv.org/pdf/1808.04537v1.pdf
PWC	https://paperswithcode.com/paper/learning-linear-transformations-for-fast
Repo	https://github.com/sunshineatnoon/LinearStyleTransfer
Framework	pytorch

Learning Stochastic Differential Equations With Gaussian Processes Without Gradient Matching


Title	Learning Stochastic Differential Equations With Gaussian Processes Without Gradient Matching
Authors	Cagatay Yildiz, Markus Heinonen, Jukka Intosalmi, Henrik Mannerström, Harri Lähdesmäki
Abstract	We introduce a novel paradigm for learning non-parametric drift and diffusion functions for stochastic differential equation (SDE). The proposed model learns to simulate path distributions that match observations with non-uniform time increments and arbitrary sparseness, which is in contrast with gradient matching that does not optimize simulated responses. We formulate sensitivity equations for learning and demonstrate that our general stochastic distribution optimisation leads to robust and efficient learning of SDE systems.
Tasks	Gaussian Processes
Published	2018-07-16
URL	http://arxiv.org/abs/1807.05748v2
PDF	http://arxiv.org/pdf/1807.05748v2.pdf
PWC	https://paperswithcode.com/paper/learning-stochastic-differential-equations
Repo	https://github.com/cagatayyildiz/npde
Framework	tf

Conversations Gone Awry: Detecting Early Signs of Conversational Failure


Title	Conversations Gone Awry: Detecting Early Signs of Conversational Failure
Authors	Justine Zhang, Jonathan P. Chang, Cristian Danescu-Niculescu-Mizil, Lucas Dixon, Yiqing Hua, Nithum Thain, Dario Taraborelli
Abstract	One of the main challenges online social systems face is the prevalence of antisocial behavior, such as harassment and personal attacks. In this work, we introduce the task of predicting from the very start of a conversation whether it will get out of hand. As opposed to detecting undesirable behavior after the fact, this task aims to enable early, actionable prediction at a time when the conversation might still be salvaged. To this end, we develop a framework for capturing pragmatic devices—such as politeness strategies and rhetorical prompts—used to start a conversation, and analyze their relation to its future trajectory. Applying this framework in a controlled setting, we demonstrate the feasibility of detecting early warning signs of antisocial behavior in online discussions.
Tasks
Published	2018-05-14
URL	http://arxiv.org/abs/1805.05345v1
PDF	http://arxiv.org/pdf/1805.05345v1.pdf
PWC	https://paperswithcode.com/paper/conversations-gone-awry-detecting-early-signs
Repo	https://github.com/canonical-debate-lab/paper
Framework	none

Learning to Perform Local Rewriting for Combinatorial Optimization


Title	Learning to Perform Local Rewriting for Combinatorial Optimization
Authors	Xinyun Chen, Yuandong Tian
Abstract	Search-based methods for hard combinatorial optimization are often guided by heuristics. Tuning heuristics in various conditions and situations is often time-consuming. In this paper, we propose NeuRewriter that learns a policy to pick heuristics and rewrite the local components of the current solution to iteratively improve it until convergence. The policy factorizes into a region-picking and a rule-picking component, each parameterized by a neural network trained with actor-critic methods in reinforcement learning. NeuRewriter captures the general structure of combinatorial problems and shows strong performance in three versatile tasks: expression simplification, online job scheduling and vehicle routing problems. NeuRewriter outperforms the expression simplification component in Z3; outperforms DeepRM and Google OR-tools in online job scheduling; and outperforms recent neural baselines and Google OR-tools in vehicle routing problems.
Tasks	Combinatorial Optimization
Published	2018-09-30
URL	https://arxiv.org/abs/1810.00337v5
PDF	https://arxiv.org/pdf/1810.00337v5.pdf
PWC	https://paperswithcode.com/paper/automatic-local-rewriting-for-combinatorial
Repo	https://github.com/facebookresearch/neural-rewriter
Framework	pytorch

Invertible Residual Networks


Title	Invertible Residual Networks
Authors	Jens Behrmann, Will Grathwohl, Ricky T. Q. Chen, David Duvenaud, Jörn-Henrik Jacobsen
Abstract	We show that standard ResNet architectures can be made invertible, allowing the same model to be used for classification, density estimation, and generation. Typically, enforcing invertibility requires partitioning dimensions or restricting network architectures. In contrast, our approach only requires adding a simple normalization step during training, already available in standard frameworks. Invertible ResNets define a generative model which can be trained by maximum likelihood on unlabeled data. To compute likelihoods, we introduce a tractable approximation to the Jacobian log-determinant of a residual block. Our empirical evaluation shows that invertible ResNets perform competitively with both state-of-the-art image classifiers and flow-based generative models, something that has not been previously achieved with a single architecture.
Tasks	Density Estimation, Image Generation
Published	2018-11-02
URL	https://arxiv.org/abs/1811.00995v3
PDF	https://arxiv.org/pdf/1811.00995v3.pdf
PWC	https://paperswithcode.com/paper/invertible-residual-networks
Repo	https://github.com/rtqichen/residual-flows
Framework	pytorch

Character-based Neural Networks for Sentence Pair Modeling


Title	Character-based Neural Networks for Sentence Pair Modeling
Authors	Wuwei Lan, Wei Xu
Abstract	Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification, semantic textual similarity, and natural language inference. Most state-of-the-art neural models for these tasks rely on pretrained word embedding and compose sentence-level semantics in varied ways; however, few works have attempted to verify whether we really need pretrained embeddings in these tasks. In this paper, we study how effective subword-level (character and character n-gram) representations are in sentence pair modeling. Though it is well-known that subword models are effective in tasks with single sentence input, including language modeling and machine translation, they have not been systematically studied in sentence pair modeling tasks where the semantic and string similarities between texts matter. Our experiments show that subword models without any pretrained word embedding can achieve new state-of-the-art results on two social media datasets and competitive results on news data for paraphrase identification.
Tasks	Language Modelling, Natural Language Inference, Paraphrase Identification, Semantic Textual Similarity, Sentence Pair Modeling
Published	2018-05-21
URL	http://arxiv.org/abs/1805.08297v1
PDF	http://arxiv.org/pdf/1805.08297v1.pdf
PWC	https://paperswithcode.com/paper/character-based-neural-networks-for-sentence
Repo	https://github.com/lanwuwei/SPM_toolkit
Framework	pytorch

Void Filling of Digital Elevation Models with Deep Generative Models


Title	Void Filling of Digital Elevation Models with Deep Generative Models
Authors	Konstantinos Gavriil, Georg Muntingh, Oliver J. D. Barrowclough
Abstract	In recent years, advances in machine learning algorithms, cheap computational resources, and the availability of big data have spurred the deep learning revolution in various application domains. In particular, supervised learning techniques in image analysis have led to superhuman performance in various tasks, such as classification, localization, and segmentation, while unsupervised learning techniques based on increasingly advanced generative models have been applied to generate high-resolution synthetic images indistinguishable from real images. In this paper we consider a state-of-the-art machine learning model for image inpainting, namely a Wasserstein Generative Adversarial Network based on a fully convolutional architecture with a contextual attention mechanism. We show that this model can successfully be transferred to the setting of digital elevation models (DEMs) for the purpose of generating semantically plausible data for filling voids. Training, testing and experimentation is done on GeoTIFF data from various regions in Norway, made openly available by the Norwegian Mapping Authority.
Tasks	Image Inpainting
Published	2018-11-30
URL	http://arxiv.org/abs/1811.12693v2
PDF	http://arxiv.org/pdf/1811.12693v2.pdf
PWC	https://paperswithcode.com/paper/void-filling-of-digital-elevation-models-with
Repo	https://github.com/konstantg/dem-fill
Framework	tf

Faster Matrix Completion Using Randomized SVD


Title	Faster Matrix Completion Using Randomized SVD
Authors	Xu Feng, Wenjian Yu, Yaohang Li
Abstract	Matrix completion is a widely used technique for image inpainting and personalized recommender system, etc. In this work, we focus on accelerating the matrix completion using faster randomized singular value decomposition (rSVD). Firstly, two fast randomized algorithms (rSVD-PI and rSVD- BKI) are proposed for handling sparse matrix. They make use of an eigSVD procedure and several accelerating skills. Then, with the rSVD-BKI algorithm and a new subspace recycling technique, we accelerate the singular value thresholding (SVT) method in [1] to realize faster matrix completion. Experiments show that the proposed rSVD algorithms can be 6X faster than the basic rSVD algorithm [2] while keeping same accuracy. For image inpainting and movie-rating estimation problems, the proposed accelerated SVT algorithm consumes 15X and 8X less CPU time than the methods using svds and lansvd respectively, without loss of accuracy.
Tasks	Image Inpainting, Matrix Completion, Recommendation Systems
Published	2018-10-16
URL	http://arxiv.org/abs/1810.06860v1
PDF	http://arxiv.org/pdf/1810.06860v1.pdf
PWC	https://paperswithcode.com/paper/faster-matrix-completion-using-randomized-svd
Repo	https://github.com/XuFengthucs/fSVT
Framework	none

Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech


Title	Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speech
Authors	Yu-An Chung, James Glass
Abstract	In this paper, we propose a novel deep neural network architecture, Speech2Vec, for learning fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain semantic information pertaining to the underlying spoken words, and are close to other vectors in the embedding space if their corresponding underlying spoken words are semantically similar. The proposed model can be viewed as a speech version of Word2Vec. Its design is based on a RNN Encoder-Decoder framework, and borrows the methodology of skipgrams or continuous bag-of-words for training. Learning word embeddings directly from speech enables Speech2Vec to make use of the semantic information carried by speech that does not exist in plain text. The learned word embeddings are evaluated and analyzed on 13 widely used word similarity benchmarks, and outperform word embeddings learned by Word2Vec from the transcriptions.
Tasks	Learning Word Embeddings, Word Embeddings
Published	2018-03-23
URL	http://arxiv.org/abs/1803.08976v2
PDF	http://arxiv.org/pdf/1803.08976v2.pdf
PWC	https://paperswithcode.com/paper/speech2vec-a-sequence-to-sequence-framework
Repo	https://github.com/iamyuanchung/speech2vec-pretrained-vectors
Framework	none

A Hybrid Frequency-domain/Image-domain Deep Network for Magnetic Resonance Image Reconstruction


Title	A Hybrid Frequency-domain/Image-domain Deep Network for Magnetic Resonance Image Reconstruction
Authors	Roberto Souza, Richard Frayne
Abstract	Decreasing magnetic resonance (MR) image acquisition times can potentially reduce procedural cost and make MR examinations more accessible. Compressed sensing (CS)-based image reconstruction methods, for example, decrease MR acquisition time by reconstructing high-quality images from data that were originally sampled at rates inferior to the Nyquist-Shannon sampling theorem. In this work we propose a hybrid architecture that works both in the k-space (or frequency-domain) and the image (or spatial) domains. Our network is composed of a complex-valued residual U-net in the k-space domain, an inverse Fast Fourier Transform (iFFT) operation, and a real-valued U-net in the image domain. Our experiments demonstrated, using MR raw k-space data, that the proposed hybrid approach can potentially improve CS reconstruction compared to deep-learning networks that operate only in the image domain. In this study we compare our method with four previously published deep neural networks and examine their ability to reconstruct images that are subsequently used to generate regional volume estimates. We evaluated undersampling ratios of 75% and 80%. Our technique was ranked second in the quantitative analysis, but qualitative analysis indicated that our reconstruction performed the best in hard to reconstruct regions, such as the cerebellum. All images reconstructed with our method were successfully post-processed, and showed good volumetry agreement compared with the fully sampled reconstruction measures.
Tasks	Image Reconstruction
Published	2018-10-30
URL	http://arxiv.org/abs/1810.12473v1
PDF	http://arxiv.org/pdf/1810.12473v1.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-frequency-domainimage-domain-deep
Repo	https://github.com/rmsouza01/Hybrid-CS-Model-MRI
Framework	tf