Paper Group AWR 217
Deep Graph Convolutional Encoders for Structured Data to Text Generation. Sorting by Swaps with Noisy Comparisons. Exploiting Local Feature Patterns for Unsupervised Domain Adaptation. Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation. Addressee and Response Selection for Multilingual Conversation. Ithemal: …
Deep Graph Convolutional Encoders for Structured Data to Text Generation
Title | Deep Graph Convolutional Encoders for Structured Data to Text Generation |
Authors | Diego Marcheggiani, Laura Perez-Beltrachini |
Abstract | Most previous work on neural text generation from graph-structured data relies on standard sequence-to-sequence methods. These approaches linearise the input graph to be fed to a recurrent neural network. In this paper, we propose an alternative encoder based on graph convolutional networks that directly exploits the input structure. We report results on two graph-to-sequence datasets that empirically show the benefits of explicitly encoding the input graph structure. |
Tasks | Data-to-Text Generation, Graph-to-Sequence, Text Generation |
Published | 2018-10-23 |
URL | http://arxiv.org/abs/1810.09995v1 |
http://arxiv.org/pdf/1810.09995v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-graph-convolutional-encoders-for |
Repo | https://github.com/diegma/graph-2-text |
Framework | pytorch |
Sorting by Swaps with Noisy Comparisons
Title | Sorting by Swaps with Noisy Comparisons |
Authors | Tomáš Gavenčiak, Barbara Geissmann, Johannes Lengler |
Abstract | We study sorting of permutations by random swaps if each comparison gives the wrong result with some fixed probability $p<1/2$. We use this process as prototype for the behaviour of randomized, comparison-based optimization heuristics in the presence of noisy comparisons. As quality measure, we compute the expected fitness of the stationary distribution. To measure the runtime, we compute the minimal number of steps after which the average fitness approximates the expected fitness of the stationary distribution. We study the process where in each round a random pair of elements at distance at most $r$ are compared. We give theoretical results for the extreme cases $r=1$ and $r=n$, and experimental results for the intermediate cases. We find a trade-off between faster convergence (for large $r$) and better quality of the solution after convergence (for small $r$). |
Tasks | |
Published | 2018-03-12 |
URL | http://arxiv.org/abs/1803.04509v1 |
http://arxiv.org/pdf/1803.04509v1.pdf | |
PWC | https://paperswithcode.com/paper/sorting-by-swaps-with-noisy-comparisons |
Repo | https://github.com/gavento/swap-sorting-experiments |
Framework | none |
Exploiting Local Feature Patterns for Unsupervised Domain Adaptation
Title | Exploiting Local Feature Patterns for Unsupervised Domain Adaptation |
Authors | Jun Wen, Risheng Liu, Nenggan Zheng, Qian Zheng, Zhefeng Gong, Junsong Yuan |
Abstract | Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local features and their multi-mode statistics. We show that the learned local feature patterns are more generic and transferable and a further local feature distribution matching enables fine-grained feature alignment. In this paper, we present a method for learning domain-invariant local feature patterns and jointly aligning holistic and local feature statistics. Comparisons to the state-of-the-art unsupervised domain adaptation methods on two popular benchmark datasets demonstrate the superiority of our approach and its effectiveness on alleviating negative transfer. |
Tasks | Domain Adaptation, Unsupervised Domain Adaptation |
Published | 2018-11-12 |
URL | http://arxiv.org/abs/1811.05042v2 |
http://arxiv.org/pdf/1811.05042v2.pdf | |
PWC | https://paperswithcode.com/paper/exploiting-local-feature-patterns-for |
Repo | https://github.com/BMerliot/master_AIC_advanced_ML |
Framework | tf |
Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation
Title | Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation |
Authors | Gregory Kahn, Adam Villaflor, Pieter Abbeel, Sergey Levine |
Abstract | A general-purpose intelligent robot must be able to learn autonomously and be able to accomplish multiple tasks in order to be deployed in the real world. However, standard reinforcement learning approaches learn separate task-specific policies and assume the reward function for each task is known a priori. We propose a framework that learns event cues from off-policy data, and can flexibly combine these event cues at test time to accomplish different tasks. These event cue labels are not assumed to be known a priori, but are instead labeled using learned models, such as computer vision detectors, and then `backed up’ in time using an action-conditioned predictive model. We show that a simulated robotic car and a real-world RC car can gather data and train fully autonomously without any human-provided labels beyond those needed to train the detectors, and then at test-time be able to accomplish a variety of different tasks. Videos of the experiments and code can be found at https://github.com/gkahn13/CAPs | |
Tasks | Robot Navigation |
Published | 2018-10-16 |
URL | http://arxiv.org/abs/1810.07167v1 |
http://arxiv.org/pdf/1810.07167v1.pdf | |
PWC | https://paperswithcode.com/paper/composable-action-conditioned-predictors |
Repo | https://github.com/gkahn13/CAPs |
Framework | none |
Addressee and Response Selection for Multilingual Conversation
Title | Addressee and Response Selection for Multilingual Conversation |
Authors | Motoki Sato, Hiroki Ouch, Yuta Tsuboi |
Abstract | Developing conversational systems that can converse in many languages is an interesting challenge for natural language processing. In this paper, we introduce multilingual addressee and response selection. In this task, a conversational system predicts an appropriate addressee and response for an input message in multiple languages. A key to developing such multilingual responding systems is how to utilize high-resource language data to compensate for low-resource language data. We present several knowledge transfer methods for conversational systems. To evaluate our methods, we create a new multilingual conversation dataset. Experiments on the dataset demonstrate the effectiveness of our methods. |
Tasks | Transfer Learning |
Published | 2018-08-12 |
URL | http://arxiv.org/abs/1808.03915v1 |
http://arxiv.org/pdf/1808.03915v1.pdf | |
PWC | https://paperswithcode.com/paper/addressee-and-response-selection-for |
Repo | https://github.com/aonotas/multilingual_ASR |
Framework | none |
Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks
Title | Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks |
Authors | Charith Mendis, Alex Renda, Saman Amarasinghe, Michael Carbin |
Abstract | Predicting the number of clock cycles a processor takes to execute a block of assembly instructions in steady state (the throughput) is important for both compiler designers and performance engineers. Building an analytical model to do so is especially complicated in modern x86-64 Complex Instruction Set Computer (CISC) machines with sophisticated processor microarchitectures in that it is tedious, error prone, and must be performed from scratch for each processor generation. In this paper we present Ithemal, the first tool which learns to predict the throughput of a set of instructions. Ithemal uses a hierarchical LSTM–based approach to predict throughput based on the opcodes and operands of instructions in a basic block. We show that Ithemal is more accurate than state-of-the-art hand-written tools currently used in compiler backends and static machine code analyzers. In particular, our model has less than half the error of state-of-the-art analytical models (LLVM’s llvm-mca and Intel’s IACA). Ithemal is also able to predict these throughput values just as fast as the aforementioned tools, and is easily ported across a variety of processor microarchitectures with minimal developer effort. |
Tasks | |
Published | 2018-08-21 |
URL | https://arxiv.org/abs/1808.07412v2 |
https://arxiv.org/pdf/1808.07412v2.pdf | |
PWC | https://paperswithcode.com/paper/ithemal-accurate-portable-and-fast-basic |
Repo | https://github.com/psg-mit/Ithemal |
Framework | pytorch |
Deep Paper Gestalt
Title | Deep Paper Gestalt |
Authors | Jia-Bin Huang |
Abstract | Recent years have witnessed a significant increase in the number of paper submissions to computer vision conferences. The sheer volume of paper submissions and the insufficient number of competent reviewers cause a considerable burden for the current peer review system. In this paper, we learn a classifier to predict whether a paper should be accepted or rejected based solely on the visual appearance of the paper (i.e., the gestalt of a paper). Experimental results show that our classifier can safely reject 50% of the bad papers while wrongly reject only 0.4% of the good papers, and thus dramatically reduce the workload of the reviewers. We also provide tools for providing suggestions to authors so that they can improve the gestalt of their papers. |
Tasks | |
Published | 2018-12-20 |
URL | http://arxiv.org/abs/1812.08775v1 |
http://arxiv.org/pdf/1812.08775v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-paper-gestalt |
Repo | https://github.com/vt-vl-lab/paper-gestalt |
Framework | none |
Reduction of Parameter Redundancy in Biaffine Classifiers with Symmetric and Circulant Weight Matrices
Title | Reduction of Parameter Redundancy in Biaffine Classifiers with Symmetric and Circulant Weight Matrices |
Authors | Tomoki Matsuno, Katsuhiko Hayashi, Takahiro Ishihara, Hitoshi Manabe, Yuji Matsumoto |
Abstract | Currently, the biaffine classifier has been attracting attention as a method to introduce an attention mechanism into the modeling of binary relations. For instance, in the field of dependency parsing, the Deep Biaffine Parser by Dozat and Manning has achieved state-of-the-art performance as a graph-based dependency parser on the English Penn Treebank and CoNLL 2017 shared task. On the other hand, it is reported that parameter redundancy in the weight matrix in biaffine classifiers, which has O(n^2) parameters, results in overfitting (n is the number of dimensions). In this paper, we attempted to reduce the parameter redundancy by assuming either symmetry or circularity of weight matrices. In our experiments on the CoNLL 2017 shared task dataset, our model achieved better or comparable accuracy on most of the treebanks with more than 16% parameter reduction. |
Tasks | Dependency Parsing |
Published | 2018-10-18 |
URL | http://arxiv.org/abs/1810.08307v1 |
http://arxiv.org/pdf/1810.08307v1.pdf | |
PWC | https://paperswithcode.com/paper/reduction-of-parameter-redundancy-in-biaffine |
Repo | https://github.com/TomokiMatsuno/PACLIC32 |
Framework | none |
FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
Title | FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification |
Authors | Yixiao Ge, Zhuowan Li, Haiyu Zhao, Guojun Yin, Shuai Yi, Xiaogang Wang, Hongsheng Li |
Abstract | Person re-identification (reID) is an important task that requires to retrieve a person’s images from an image dataset, given one image of the person of interest. For learning robust person features, the pose variation of person images is one of the key challenges. Existing works targeting the problem either perform human alignment, or learn human-region-based representations. Extra pose information and computational cost is generally required for inference. To solve this issue, a Feature Distilling Generative Adversarial Network (FD-GAN) is proposed for learning identity-related and pose-unrelated representations. It is a novel framework based on a Siamese structure with multiple novel discriminators on human poses and identities. In addition to the discriminators, a novel same-pose loss is also integrated, which requires appearance of a same person’s generated images to be similar. After learning pose-unrelated person features with pose guidance, no auxiliary pose information and additional computational cost is required during testing. Our proposed FD-GAN achieves state-of-the-art performance on three person reID datasets, which demonstrates that the effectiveness and robust feature distilling capability of the proposed FD-GAN. |
Tasks | Person Re-Identification |
Published | 2018-10-06 |
URL | http://arxiv.org/abs/1810.02936v2 |
http://arxiv.org/pdf/1810.02936v2.pdf | |
PWC | https://paperswithcode.com/paper/fd-gan-pose-guided-feature-distilling-gan-for |
Repo | https://github.com/yxgeee/FD-GAN |
Framework | pytorch |
Image Super-Resolution Using Very Deep Residual Channel Attention Networks
Title | Image Super-Resolution Using Very Deep Residual Channel Attention Networks |
Authors | Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, Yun Fu |
Abstract | Convolutional neural network (CNN) depth is of crucial importance for image super-resolution (SR). However, we observe that deeper networks for image SR are more difficult to train. The low-resolution inputs and features contain abundant low-frequency information, which is treated equally across channels, hence hindering the representational ability of CNNs. To solve these problems, we propose the very deep residual channel attention networks (RCAN). Specifically, we propose a residual in residual (RIR) structure to form very deep network, which consists of several residual groups with long skip connections. Each residual group contains some residual blocks with short skip connections. Meanwhile, RIR allows abundant low-frequency information to be bypassed through multiple skip connections, making the main network focus on learning high-frequency information. Furthermore, we propose a channel attention mechanism to adaptively rescale channel-wise features by considering interdependencies among channels. Extensive experiments show that our RCAN achieves better accuracy and visual improvements against state-of-the-art methods. |
Tasks | Image Super-Resolution, Super-Resolution |
Published | 2018-07-08 |
URL | http://arxiv.org/abs/1807.02758v2 |
http://arxiv.org/pdf/1807.02758v2.pdf | |
PWC | https://paperswithcode.com/paper/image-super-resolution-using-very-deep |
Repo | https://github.com/yulunzhang/RCAN |
Framework | pytorch |
Reservoir computing approaches for representation and classification of multivariate time series
Title | Reservoir computing approaches for representation and classification of multivariate time series |
Authors | Filippo Maria Bianchi, Simone Scardapane, Sigurd Løkse, Robert Jenssen |
Abstract | Classification of multivariate time series (MTS) has been tackled with a large variety of methodologies and applied to a wide range of scenarios. Among the existing approaches, reservoir computing (RC) techniques, which implement a fixed and high-dimensional recurrent network to process sequential data, are computationally efficient tools to generate a vectorial, fixed-size representation of the MTS that can be further processed by standard classifiers. Despite their unrivaled training speed, MTS classifiers based on a standard RC architecture fail to achieve the same accuracy of other classifiers, such as those exploiting fully trainable recurrent networks. In this paper we introduce the reservoir model space, an RC approach to learn vectorial representations of MTS in an unsupervised fashion. Each MTS is encoded within the parameters of a linear model trained to predict a low-dimensional embedding of the reservoir dynamics. Our model space yields a powerful representation of the MTS and, thanks to an intermediate dimensionality reduction procedure, attains computational performance comparable to other RC methods. As a second contribution we propose a modular RC framework for MTS classification, with an associated open source Python library. By combining the different modules it is possible to seamlessly implement advanced RC architectures, including our proposed unsupervised representation, bidirectional reservoirs, and non-linear readouts, such as deep neural networks with both fixed and flexible activation functions. Results obtained on benchmark and real-world MTS datasets show that RC classifiers are dramatically faster and, when implemented using our proposed representation, also achieve superior classification accuracy. |
Tasks | Dimensionality Reduction, Time Series |
Published | 2018-03-21 |
URL | http://arxiv.org/abs/1803.07870v2 |
http://arxiv.org/pdf/1803.07870v2.pdf | |
PWC | https://paperswithcode.com/paper/reservoir-computing-approaches-for |
Repo | https://github.com/FilippoMB/Reservoir-Computing-framework-for-multivariate-time-series-classification |
Framework | tf |
Adversarial Sample Detection for Deep Neural Network through Model Mutation Testing
Title | Adversarial Sample Detection for Deep Neural Network through Model Mutation Testing |
Authors | Jingyi Wang, Guoliang Dong, Jun Sun, Xinyu Wang, Peixin Zhang |
Abstract | Deep neural networks (DNN) have been shown to be useful in a wide range of applications. However, they are also known to be vulnerable to adversarial samples. By transforming a normal sample with some carefully crafted human imperceptible perturbations, even highly accurate DNN make wrong decisions. Multiple defense mechanisms have been proposed which aim to hinder the generation of such adversarial samples. However, a recent work show that most of them are ineffective. In this work, we propose an alternative approach to detect adversarial samples at runtime. Our main observation is that adversarial samples are much more sensitive than normal samples if we impose random mutations on the DNN. We thus first propose a measure of `sensitivity’ and show empirically that normal samples and adversarial samples have distinguishable sensitivity. We then integrate statistical hypothesis testing and model mutation testing to check whether an input sample is likely to be normal or adversarial at runtime by measuring its sensitivity. We evaluated our approach on the MNIST and CIFAR10 datasets. The results show that our approach detects adversarial samples generated by state-of-the-art attacking methods efficiently and accurately. | |
Tasks | |
Published | 2018-12-14 |
URL | http://arxiv.org/abs/1812.05793v2 |
http://arxiv.org/pdf/1812.05793v2.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-sample-detection-for-deep-neural |
Repo | https://github.com/KuoTzu-yang/DeepMutation |
Framework | tf |
Impact of Corpora Quality on Neural Machine Translation
Title | Impact of Corpora Quality on Neural Machine Translation |
Authors | Matīss Rikters |
Abstract | Large parallel corpora that are automatically obtained from the web, documents or elsewhere often exhibit many corrupted parts that are bound to negatively affect the quality of the systems and models that learn from these corpora. This paper describes frequent problems found in data and such data affects neural machine translation systems, as well as how to identify and deal with them. The solutions are summarised in a set of scripts that remove problematic sentences from input corpora. |
Tasks | Machine Translation |
Published | 2018-10-19 |
URL | http://arxiv.org/abs/1810.08392v1 |
http://arxiv.org/pdf/1810.08392v1.pdf | |
PWC | https://paperswithcode.com/paper/impact-of-corpora-quality-on-neural-machine |
Repo | https://github.com/M4t1ss/parallel-corpora-tools |
Framework | none |
Optical Flow Dataset and Benchmark for Visual Crowd Analysis
Title | Optical Flow Dataset and Benchmark for Visual Crowd Analysis |
Authors | Gregory Schröder, Tobias Senst, Erik Bochinski, Thomas Sikora |
Abstract | The performance of optical flow algorithms greatly depends on the specifics of the content and the application for which it is used. Existing and well established optical flow datasets are limited to rather particular contents from which none is close to crowd behavior analysis; whereas such applications heavily utilize optical flow. We introduce a new optical flow dataset exploiting the possibilities of a recent video engine to generate sequences with ground-truth optical flow for large crowds in different scenarios. We break with the development of the last decade of introducing ever increasing displacements to pose new difficulties. Instead we focus on real-world surveillance scenarios where numerous small, partly independent, non rigidly moving objects observed over a long temporal range pose a challenge. By evaluating different optical flow algorithms, we find that results of established datasets can not be transferred to these new challenges. In exhaustive experiments we are able to provide new insight into optical flow for crowd analysis. Finally, the results have been validated on the real-world UCF crowd tracking benchmark while achieving competitive results compared to more sophisticated state-of-the-art crowd tracking approaches. |
Tasks | Optical Flow Estimation, Visual Crowd Analysis |
Published | 2018-11-17 |
URL | http://arxiv.org/abs/1811.07170v1 |
http://arxiv.org/pdf/1811.07170v1.pdf | |
PWC | https://paperswithcode.com/paper/optical-flow-dataset-and-benchmark-for-visual |
Repo | https://github.com/tsenst/CrowdFlow |
Framework | none |
Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications
Title | Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications |
Authors | Thanh Thi Nguyen, Ngoc Duy Nguyen, Saeid Nahavandi |
Abstract | Reinforcement learning (RL) algorithms have been around for decades and employed to solve various sequential decision-making problems. These algorithms however have faced great challenges when dealing with high-dimensional environments. The recent development of deep learning has enabled RL methods to drive optimal policies for sophisticated and capable agents, which can perform efficiently in these challenging environments. This paper addresses an important aspect of deep RL related to situations that require multiple agents to communicate and cooperate to solve complex tasks. A survey of different approaches to problems related to multi-agent deep RL (MADRL) is presented, including non-stationarity, partial observability, continuous state and action spaces, multi-agent training schemes, multi-agent transfer learning. The merits and demerits of the reviewed methods will be analyzed and discussed, with their corresponding applications explored. It is envisaged that this review provides insights about various MADRL methods and can lead to future development of more robust and highly useful multi-agent learning methods for solving real-world problems. |
Tasks | Decision Making, Transfer Learning |
Published | 2018-12-31 |
URL | http://arxiv.org/abs/1812.11794v2 |
http://arxiv.org/pdf/1812.11794v2.pdf | |
PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-multi-agent |
Repo | https://github.com/nsrishankar/rl_swarm_papers |
Framework | none |