October 20, 2019

2960 words 14 mins read

Paper Group AWR 189

Extending Stan for Deep Probabilistic Programming. Strong Baselines for Neural Semi-supervised Learning under Domain Shift. Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss. A Span-Extraction Dataset for Chinese Machine Reading Comprehension. Fast Non-Bayesian Poisson Factorization for Implicit-Feedback Recommendations. LPRN …

Extending Stan for Deep Probabilistic Programming


Title	Extending Stan for Deep Probabilistic Programming
Authors	Javier Burroni, Guillaume Baudart, Louis Mandel, Martin Hirzel, Avraham Shinnar
Abstract	Deep probabilistic programming combines deep neural networks (for automatic hierarchical representation learning) with probabilistic models (for principled handling of uncertainty). Unfortunately, it is difficult to write deep probabilistic models, because existing programming frameworks lack concise, high-level, and clean ways to express them. To ease this task, we extend Stan, a popular high-level probabilistic programming language, to use deep neural networks written in PyTorch. Training deep probabilistic models works best with variational inference, so we also extend Stan for that. We implement these extensions by translating Stan programs to Pyro. Our translation clarifies the relationship between different families of probabilistic programming languages. Overall, our paper is a step towards making deep probabilistic programming easier.
Tasks	Probabilistic Programming, Representation Learning
Published	2018-09-30
URL	http://arxiv.org/abs/1810.00873v1
PDF	http://arxiv.org/pdf/1810.00873v1.pdf
PWC	https://paperswithcode.com/paper/extending-stan-for-deep-probabilistic
Repo	https://github.com/deepppl/deepppl
Framework	pytorch

Strong Baselines for Neural Semi-supervised Learning under Domain Shift


Title	Strong Baselines for Neural Semi-supervised Learning under Domain Shift
Authors	Sebastian Ruder, Barbara Plank
Abstract	Novel neural models have been proposed in recent years for learning under domain shift. Most models, however, only evaluate on a single task, on proprietary datasets, or compare to weak baselines, which makes comparison of models difficult. In this paper, we re-evaluate classic general-purpose bootstrapping approaches in the context of neural networks under domain shifts vs. recent neural approaches and propose a novel multi-task tri-training method that reduces the time and space complexity of classic tri-training. Extensive experiments on two benchmarks are negative: while our novel method establishes a new state-of-the-art for sentiment analysis, it does not fare consistently the best. More importantly, we arrive at the somewhat surprising conclusion that classic tri-training, with some additions, outperforms the state of the art. We conclude that classic approaches constitute an important and strong baseline.
Tasks	Sentiment Analysis
Published	2018-04-25
URL	http://arxiv.org/abs/1804.09530v1
PDF	http://arxiv.org/pdf/1804.09530v1.pdf
PWC	https://paperswithcode.com/paper/strong-baselines-for-neural-semi-supervised
Repo	https://github.com/ambujojha/SemiSupervisedLearning
Framework	pytorch

Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss


Title	Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss
Authors	Peng Xu, Denilson Barbosa
Abstract	The task of Fine-grained Entity Type Classification (FETC) consists of assigning types from a hierarchy to entity mentions in text. Existing methods rely on distant supervision and are thus susceptible to noisy labels that can be out-of-context or overly-specific for the training sentence. Previous methods that attempt to address these issues do so with heuristics or with the help of hand-crafted features. Instead, we propose an end-to-end solution with a neural network model that uses a variant of cross- entropy loss function to handle out-of-context labels, and hierarchical loss normalization to cope with overly-specific ones. Also, previous work solve FETC a multi-label classification followed by ad-hoc post-processing. In contrast, our solution is more elegant: we use public word embeddings to train a single-label that jointly learns representations for entity mentions and their context. We show experimentally that our approach is robust against noise and consistently outperforms the state-of-the-art on established benchmarks for the task.
Tasks	Multi-Label Classification, Word Embeddings
Published	2018-03-09
URL	http://arxiv.org/abs/1803.03378v2
PDF	http://arxiv.org/pdf/1803.03378v2.pdf
PWC	https://paperswithcode.com/paper/neural-fine-grained-entity-type
Repo	https://github.com/YoungXiyuan/DCA
Framework	pytorch

A Span-Extraction Dataset for Chinese Machine Reading Comprehension


Title	A Span-Extraction Dataset for Chinese Machine Reading Comprehension
Authors	Yiming Cui, Ting Liu, Wanxiang Che, Li Xiao, Zhipeng Chen, Wentao Ma, Shijin Wang, Guoping Hu
Abstract	Machine Reading Comprehension (MRC) has become enormously popular recently and has attracted a lot of attention. However, the existing reading comprehension datasets are mostly in English. In this paper, we introduce a Span-Extraction dataset for Chinese machine reading comprehension to add language diversities in this area. The dataset is composed by near 20,000 real questions annotated on Wikipedia paragraphs by human experts. We also annotated a challenge set which contains the questions that need comprehensive understanding and multi-sentence inference throughout the context. We present several baseline systems as well as anonymous submissions for demonstrating the difficulties in this dataset. With the release of the dataset, we hosted the Second Evaluation Workshop on Chinese Machine Reading Comprehension (CMRC 2018). We hope the release of the dataset could further accelerate the Chinese machine reading comprehension research. Resources are available: https://github.com/ymcui/cmrc2018
Tasks	Machine Reading Comprehension, Reading Comprehension
Published	2018-10-17
URL	https://arxiv.org/abs/1810.07366v2
PDF	https://arxiv.org/pdf/1810.07366v2.pdf
PWC	https://paperswithcode.com/paper/a-span-extraction-dataset-for-chinese-machine
Repo	https://github.com/ymcui/cmrc2018
Framework	tf

Fast Non-Bayesian Poisson Factorization for Implicit-Feedback Recommendations


Title	Fast Non-Bayesian Poisson Factorization for Implicit-Feedback Recommendations
Authors	David Cortes
Abstract	This work explores non-negative matrix factorization based on regularized Poisson models for recommender systems with implicit-feedback data. The properties of Poisson likelihood allow a shortcut for very fast computation and optimization over elements with zero-value when the latent-factor matrices are non-negative, making it a more suitable approach than squared loss for very sparse inputs such as implicit-feedback data. A simple and embarrassingly parallel optimization approach based on proximal gradients is presented, which in large datasets converges 2-3 orders of magnitude faster than its Bayesian counterpart (Hierarchical Poisson Factorization) fit through variational inference techniques, and 1 order of magnitude faster than implicit-ALS fit with the Conjugate Gradient method.
Tasks	Recommendation Systems
Published	2018-11-05
URL	https://arxiv.org/abs/1811.01908v2
PDF	https://arxiv.org/pdf/1811.01908v2.pdf
PWC	https://paperswithcode.com/paper/fast-non-bayesian-poisson-factorization-for
Repo	https://github.com/david-cortes/poismf
Framework	none

LPRNet: License Plate Recognition via Deep Neural Networks


Title	LPRNet: License Plate Recognition via Deep Neural Networks
Authors	Sergey Zherzdev, Alexey Gruzdev
Abstract	This paper proposes LPRNet - end-to-end method for Automatic License Plate Recognition without preliminary character segmentation. Our approach is inspired by recent breakthroughs in Deep Neural Networks, and works in real-time with recognition accuracy up to 95% for Chinese license plates: 3 ms/plate on nVIDIA GeForce GTX 1080 and 1.3 ms/plate on Intel Core i7-6700K CPU. LPRNet consists of the lightweight Convolutional Neural Network, so it can be trained in end-to-end way. To the best of our knowledge, LPRNet is the first real-time License Plate Recognition system that does not use RNNs. As a result, the LPRNet algorithm may be used to create embedded solutions for LPR that feature high level accuracy even on challenging Chinese license plates.
Tasks	License Plate Recognition
Published	2018-06-27
URL	http://arxiv.org/abs/1806.10447v1
PDF	http://arxiv.org/pdf/1806.10447v1.pdf
PWC	https://paperswithcode.com/paper/lprnet-license-plate-recognition-via-deep
Repo	https://github.com/tn00378077/licenses
Framework	none

Deep Architectures for Learning Context-dependent Ranking Functions


Title	Deep Architectures for Learning Context-dependent Ranking Functions
Authors	Karlson Pfannschmidt, Pritha Gupta, Eyke Hüllermeier
Abstract	Object ranking is an important problem in the realm of preference learning. On the basis of training data in the form of a set of rankings of objects, which are typically represented as feature vectors, the goal is to learn a ranking function that predicts a linear order of any new set of objects. Current approaches commonly focus on ranking by scoring, i.e., on learning an underlying latent utility function that seeks to capture the inherent utility of each object. These approaches, however, are not able to take possible effects of context-dependence into account, where context-dependence means that the utility or usefulness of an object may also depend on what other objects are available as alternatives. In this paper, we formalize the problem of context-dependent ranking and present two general approaches based on two natural representations of context-dependent ranking functions. Both approaches are instantiated by means of appropriate neural network architectures, which are evaluated on suitable benchmark task.
Tasks
Published	2018-03-15
URL	http://arxiv.org/abs/1803.05796v2
PDF	http://arxiv.org/pdf/1803.05796v2.pdf
PWC	https://paperswithcode.com/paper/deep-architectures-for-learning-context
Repo	https://github.com/kiudee/cs-ranking
Framework	tf

Learn to Interpret Atari Agents


Title	Learn to Interpret Atari Agents
Authors	Zhao Yang, Song Bai, Li Zhang, Philip H. S. Torr
Abstract	Deep Reinforcement Learning (DeepRL) agents surpass human-level performances in a multitude of tasks. However, the direct mapping from states to actions makes it hard to interpret the rationale behind the decision making of agents. In contrast to previous a-posteriori methods of visualizing DeepRL policies, we propose an end-to-end trainable framework based on Rainbow, a representative Deep Q-Network (DQN) agent. Our method automatically learns important regions in the input domain, which enables characterizations of the decision making and interpretations for non-intuitive behaviors. Hence we name it Region Sensitive Rainbow (RS-Rainbow). RS-Rainbow utilizes a simple yet effective mechanism to incorporate visualization ability into the learning model, not only improving model interpretability, but leading to improved performance. Extensive experiments on the challenging platform of Atari 2600 demonstrate the superiority of RS-Rainbow. In particular, our agent achieves state of the art at just 25% of the training frames. Demonstrations and code are available at https://github.com/yz93/Learn-to-Interpret-Atari-Agents.
Tasks	Decision Making
Published	2018-12-29
URL	http://arxiv.org/abs/1812.11276v2
PDF	http://arxiv.org/pdf/1812.11276v2.pdf
PWC	https://paperswithcode.com/paper/learn-to-interpret-atari-agents
Repo	https://github.com/yz93/Learn-to-Interpret-Atari-Agents
Framework	pytorch

Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media


Title	Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media
Authors	Shaoxing Mo, Yinhao Zhu, Nicholas Zabaras, Xiaoqing Shi, Jichun Wu
Abstract	Surrogate strategies are used widely for uncertainty quantification of groundwater models in order to improve computational efficiency. However, their application to dynamic multiphase flow problems is hindered by the curse of dimensionality, the saturation discontinuity due to capillarity effects, and the time-dependence of the multi-output responses. In this paper, we propose a deep convolutional encoder-decoder neural network methodology to tackle these issues. The surrogate modeling task is transformed to an image-to-image regression strategy. This approach extracts high-level coarse features from the high-dimensional input permeability images using an encoder, and then refines the coarse features to provide the output pressure/saturation images through a decoder. A training strategy combining a regression loss and a segmentation loss is proposed in order to better approximate the discontinuous saturation field. To characterize the high-dimensional time-dependent outputs of the dynamic system, time is treated as an additional input to the network that is trained using pairs of input realizations and of the corresponding system outputs at a limited number of time instances. The proposed method is evaluated using a geological carbon storage process-based multiphase flow model with a 2500-dimensional stochastic permeability field. With a relatively small number of training data, the surrogate model is capable of accurately characterizing the spatio-temporal evolution of the pressure and discontinuous CO2 saturation fields and can be used efficiently to compute the statistics of the system responses.
Tasks
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00882v1
PDF	http://arxiv.org/pdf/1807.00882v1.pdf
PWC	https://paperswithcode.com/paper/deep-convolutional-encoder-decoder-networks
Repo	https://github.com/cics-nd/dcedn-gcs
Framework	pytorch

Learning to Extract a Video Sequence from a Single Motion-Blurred Image


Title	Learning to Extract a Video Sequence from a Single Motion-Blurred Image
Authors	Meiguang Jin, Givi Meishvili, Paolo Favaro
Abstract	We present a method to extract a video sequence from a single motion-blurred image. Motion-blurred images are the result of an averaging process, where instant frames are accumulated over time during the exposure of the sensor. Unfortunately, reversing this process is nontrivial. Firstly, averaging destroys the temporal ordering of the frames. Secondly, the recovery of a single frame is a blind deconvolution task, which is highly ill-posed. We present a deep learning scheme that gradually reconstructs a temporal ordering by sequentially extracting pairs of frames. Our main contribution is to introduce loss functions invariant to the temporal order. This lets a neural network choose during training what frame to output among the possible combinations. We also address the ill-posedness of deblurring by designing a network with a large receptive field and implemented via resampling to achieve a higher computational efficiency. Our proposed method can successfully retrieve sharp image sequences from a single motion blurred image and can generalize well on synthetic and real datasets captured with different cameras.
Tasks	Deblurring
Published	2018-04-11
URL	http://arxiv.org/abs/1804.04065v1
PDF	http://arxiv.org/pdf/1804.04065v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-extract-a-video-sequence-from-a
Repo	https://github.com/MeiguangJin/Learning-to-Extract-a-Video-Sequence-from-a-Single-Motion-Blurred-Image
Framework	pytorch

Adversarial Spatio-Temporal Learning for Video Deblurring


Title	Adversarial Spatio-Temporal Learning for Video Deblurring
Authors	Kaihao Zhang, Wenhan Luo, Yiran Zhong, Lin Ma, Wei Liu, Hongdong Li
Abstract	Camera shake or target movement often leads to undesired blur effects in videos captured by a hand-held camera. Despite significant efforts having been devoted to video-deblur research, two major challenges remain: 1) how to model the spatio-temporal characteristics across both the spatial domain (i.e., image plane) and temporal domain (i.e., neighboring frames), and 2) how to restore sharp image details w.r.t. the conventionally adopted metric of pixel-wise errors. In this paper, to address the first challenge, we propose a DeBLuRring Network (DBLRNet) for spatial-temporal learning by applying a modified 3D convolution to both spatial and temporal domains. Our DBLRNet is able to capture jointly spatial and temporal information encoded in neighboring frames, which directly contributes to improved video deblur performance. To tackle the second challenge, we leverage the developed DBLRNet as a generator in the GAN (generative adversarial network) architecture, and employ a content loss in addition to an adversarial loss for efficient adversarial training. The developed network, which we name as DeBLuRring Generative Adversarial Network (DBLRGAN), is tested on two standard benchmarks and achieves the state-of-the-art performance.
Tasks	Deblurring
Published	2018-03-28
URL	http://arxiv.org/abs/1804.00533v2
PDF	http://arxiv.org/pdf/1804.00533v2.pdf
PWC	https://paperswithcode.com/paper/adversarial-spatio-temporal-learning-for
Repo	https://github.com/themathgeek13/STdeblur
Framework	pytorch

Few-Shot Generalization Across Dialogue Tasks


Title	Few-Shot Generalization Across Dialogue Tasks
Authors	Vladimir Vlasov, Akela Drissner-Schmid, Alan Nichol
Abstract	Machine-learning based dialogue managers are able to learn complex behaviors in order to complete a task, but it is not straightforward to extend their capabilities to new domains. We investigate different policies’ ability to handle uncooperative user behavior, and how well expertise in completing one task (such as restaurant reservations) can be reapplied when learning a new one (e.g. booking a hotel). We introduce the Recurrent Embedding Dialogue Policy (REDP), which embeds system actions and dialogue states in the same vector space. REDP contains a memory component and attention mechanism based on a modified Neural Turing Machine, and significantly outperforms a baseline LSTM classifier on this task. We also show that both our architecture and baseline solve the bAbI dialogue task, achieving 100% test accuracy.
Tasks
Published	2018-11-28
URL	http://arxiv.org/abs/1811.11707v1
PDF	http://arxiv.org/pdf/1811.11707v1.pdf
PWC	https://paperswithcode.com/paper/few-shot-generalization-across-dialogue-tasks
Repo	https://github.com/RasaHQ/conversational-ai-workshop-18
Framework	none

A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling


Title	A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling
Authors	Judith Bütepage, Hedvig Kjellström, Danica Kragic
Abstract	Human behavior is a continuous stochastic spatio-temporal process which is governed by semantic actions and affordances as well as latent factors. Therefore, video-based human activity modeling is concerned with a number of tasks such as inferring current and future semantic labels, predicting future continuous observations as well as imagining possible future label and feature sequences. In this paper we present a semi-supervised probabilistic deep latent variable model that can represent both discrete labels and continuous observations as well as latent dynamics over time. This allows the model to solve several tasks at once without explicit fine-tuning. We focus here on the tasks of action classification, detection, prediction and anticipation as well as motion prediction and synthesis based on 3D human activity data recorded with Kinect. We further extend the model to capture hierarchical label structure and to model the dependencies between multiple entities, such as a human and objects. Our experiments demonstrate that our principled approach to human activity modeling can be used to detect current and anticipate future semantic labels and to predict and synthesize future label and feature sequences. When comparing our model to state-of-the-art approaches, which are specifically designed for e.g. action classification, we find that our probabilistic formulation outperforms or is comparable to these task specific models.
Tasks	Action Classification, motion prediction, Trajectory Prediction
Published	2018-09-24
URL	http://arxiv.org/abs/1809.08875v3
PDF	http://arxiv.org/pdf/1809.08875v3.pdf
PWC	https://paperswithcode.com/paper/classify-predict-detect-anticipate-and
Repo	https://github.com/jbutepage/semi_supervised_variational_recurrent_neural_network
Framework	tf

Reward learning from human preferences and demonstrations in Atari


Title	Reward learning from human preferences and demonstrations in Atari
Authors	Borja Ibarz, Jan Leike, Tobias Pohlen, Geoffrey Irving, Shane Legg, Dario Amodei
Abstract	To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions. Instead, we can have humans communicate an objective to the agent directly. In this work, we combine two approaches to learning from human feedback: expert demonstrations and trajectory preferences. We train a deep neural network to model the reward function and use its predicted reward to train an DQN-based deep reinforcement learning agent on 9 Atari games. Our approach beats the imitation learning baseline in 7 games and achieves strictly superhuman performance on 2 games without using game rewards. Additionally, we investigate the goodness of fit of the reward model, present some reward hacking problems, and study the effects of noise in the human labels.
Tasks	Atari Games, Imitation Learning
Published	2018-11-15
URL	http://arxiv.org/abs/1811.06521v1
PDF	http://arxiv.org/pdf/1811.06521v1.pdf
PWC	https://paperswithcode.com/paper/reward-learning-from-human-preferences-and
Repo	https://github.com/rddy/ReQueST
Framework	tf

Interpretable Almost Matching Exactly for Causal Inference


Title	Interpretable Almost Matching Exactly for Causal Inference
Authors	Yameng Liu, Aw Dieng, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky
Abstract	We aim to create the highest possible quality of treatment-control matches for categorical data in the potential outcomes framework. Matching methods are heavily used in the social sciences due to their interpretability, but most matching methods do not pass basic sanity checks: they fail when irrelevant variables are introduced, and tend to be either computationally slow or produce low-quality matches. The method proposed in this work aims to match units on a weighted Hamming distance, taking into account the relative importance of the covariates; the algorithm aims to match units on as many relevant variables as possible. To do this, the algorithm creates a hierarchy of covariate combinations on which to match (similar to downward closure), in the process solving an optimization problem for each unit in order to construct the optimal matches. The algorithm uses a single dynamic program to solve all of the optimization problems simultaneously. Notable advantages of our method over existing matching procedures are its high-quality matches, versatility in handling different data distributions that may have irrelevant variables, and ability to handle missing data by matching on as many available covariates as possible.
Tasks	Causal Inference
Published	2018-06-18
URL	https://arxiv.org/abs/1806.06802v6
PDF	https://arxiv.org/pdf/1806.06802v6.pdf
PWC	https://paperswithcode.com/paper/almost-exact-matching-with-replacement-for
Repo	https://github.com/almostExactMatch/collapsingFLAME
Framework	none