Paper Group NAWR 38
Decoding P300 Variability using Convolutional Neural Networks. Optimizing Generalized Rate Metrics with Three Players. Adaptive Auxiliary Task Weighting for Reinforcement Learning. A Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation. DeepWave: A Recurrent Neural-Network for Real-Time Acoustic Imaging. AGEM: Solv …
Decoding P300 Variability using Convolutional Neural Networks
| Title | Decoding P300 Variability using Convolutional Neural Networks |
| Authors | Amelia J. Solon, Vernon J. Lawhern, Jonathan Touryan, Jonathan R. McDaniel, Anthony J. Ries, Stephen M. Gordon |
| Abstract | Deep convolutional neural networks (CNN) have previously been shown to be useful tools for signal decoding and analysis in a variety of complex domains, such as image processing and speech recognition. By learning from large amounts of data, the representations encoded by these deep networks are often invariant to moderate changes in the underlying feature spaces. Recently, we proposed a CNN architecture that could be applied to electroencephalogram (EEG) decoding and analysis. In this article, we train our CNN model using data from prior experiments in order to later decode the P300 evoked response from an unseen, hold-out experiment. We analyze the CNN output as a function of the underlying variability in the P300 response and demonstrate that the CNN output is sensitive to the experiment-induced changes in the neural response. We then assess the utility of our approach as a means of improving the overall signal-to-noise ratio in the EEG record. Finally, we show an example of how CNN-based decoding can be applied to the analysis of complex data. |
| Tasks | EEG, Eeg Decoding, Speech Recognition |
| Published | 2019-06-14 |
| URL | http://dx.doi.org/10.3389/fnhum.2019.00201 |
| https://www.frontiersin.org/articles/10.3389/fnhum.2019.00201/pdf | |
| PWC | https://paperswithcode.com/paper/decoding-p300-variability-using-convolutional |
| Repo | https://github.com/vlawhern/arl-eegmodels |
| Framework | tf |
Optimizing Generalized Rate Metrics with Three Players
| Title | Optimizing Generalized Rate Metrics with Three Players |
| Authors | Harikrishna Narasimhan, Andrew Cotter, Maya Gupta |
| Abstract | We present a general framework for solving a large class of learning problems with non-linear functions of classification rates. This includes problems where one wishes to optimize a non-decomposable performance metric such as the F-measure or G-mean, and constrained training problems where the classifier needs to satisfy non-linear rate constraints such as predictive parity fairness, distribution divergences or churn ratios. We extend previous two-player game approaches for constrained optimization to an approach with three players to decouple the classifier rates from the non-linear objective, and seek to find an equilibrium of the game. Our approach generalizes many existing algorithms, and makes possible new algorithms with more flexibility and tighter handling of non-linear rate constraints. We provide convergence guarantees for convex functions of rates, and show how our methodology can be extended to handle sums-of-ratios of rates. Experiments on different fairness tasks confirm the efficacy of our approach. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9258-optimizing-generalized-rate-metrics-with-three-players |
| http://papers.nips.cc/paper/9258-optimizing-generalized-rate-metrics-with-three-players.pdf | |
| PWC | https://paperswithcode.com/paper/optimizing-generalized-rate-metrics-with |
| Repo | https://github.com/google-research/google-research |
| Framework | tf |
Adaptive Auxiliary Task Weighting for Reinforcement Learning
| Title | Adaptive Auxiliary Task Weighting for Reinforcement Learning |
| Authors | Xingyu Lin, Harjatin Baweja, George Kantor, David Held |
| Abstract | Reinforcement learning is known to be sample inefficient, preventing its application to many real-world problems, especially with high dimensional observations like images. Transferring knowledge from other auxiliary tasks is a powerful tool for improving the learning efficiency. However, the usage of auxiliary tasks has been limited so far due to the difficulty in selecting and combining different auxiliary tasks. In this work, we propose a principled online learning algorithm that dynamically combines different auxiliary tasks to speed up training for reinforcement learning. Our method is based on the idea that auxiliary tasks should provide gradient directions that, in the long term, help to decrease the loss of the main task. We show in various environments that our algorithm can effectively combine a variety of different auxiliary tasks and achieves significant speedup compared to previous heuristic approches of adapting auxiliary task weights. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8724-adaptive-auxiliary-task-weighting-for-reinforcement-learning |
| http://papers.nips.cc/paper/8724-adaptive-auxiliary-task-weighting-for-reinforcement-learning.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-auxiliary-task-weighting-for |
| Repo | https://github.com/Xingyu-Lin/auxiliary-tasks-rl |
| Framework | none |
A Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation
| Title | A Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation |
| Authors | Xueying Bai, Jian Guan, Hongning Wang |
| Abstract | Reinforcement learning is effective in optimizing policies for recommender systems. Current solutions mostly focus on model-free approaches, which require frequent interactions with a real environment, and thus are expensive in model learning. Offline evaluation methods, such as importance sampling, can alleviate such limitations, but usually request a large amount of logged data and do not work well when the action space is large. In this work, we propose a model-based reinforcement learning solution which models the user-agent interaction for offline policy learning via a generative adversarial network. To reduce bias in the learnt policy, we use the discriminator to evaluate the quality of generated sequences and rescale the generated rewards. Our theoretical analysis and empirical evaluations demonstrate the effectiveness of our solution in identifying patterns from given offline data and learning policies based on the offline and generated data. |
| Tasks | Recommendation Systems |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9257-a-model-based-reinforcement-learning-with-adversarial-training-for-online-recommendation |
| http://papers.nips.cc/paper/9257-a-model-based-reinforcement-learning-with-adversarial-training-for-online-recommendation.pdf | |
| PWC | https://paperswithcode.com/paper/a-model-based-reinforcement-learning-with-1 |
| Repo | https://github.com/JianGuanTHU/IRecGAN |
| Framework | tf |
DeepWave: A Recurrent Neural-Network for Real-Time Acoustic Imaging
| Title | DeepWave: A Recurrent Neural-Network for Real-Time Acoustic Imaging |
| Authors | Matthieu Simeoni, Sepand Kashani, Paul Hurley, Martin Vetterli |
| Abstract | We propose a recurrent neural-network for real-time reconstruction of acoustic camera spherical maps. The network, dubbed DeepWave, is both physically and algorithmically motivated: its recurrent architecture mimics iterative solvers from convex optimisation, and its parsimonious parametrisation is based on the natural structure of acoustic imaging problems. Each network layer applies successive filtering, biasing and activation steps to its input, which can be interpreted as generalised deblurring and sparsification steps. To comply with the irregular geometry of spherical maps, filtering operations are implemented efficiently by means of graph signal processing techniques. Unlike commonly-used imaging network architectures, DeepWave is moreover capable of directly processing the complex-valued raw microphone correlations, learning how to optimally back-project these into a spherical map. We propose moreover a smart physically-inspired initialisation scheme that attains much faster training and higher performance than random initialisation. Our real-data experiments show DeepWave has similar computational speed to the state-of-the-art delay-and-sum imager with vastly superior resolution. While developed primarily for acoustic cameras, DeepWave could easily be adapted to neighbouring signal processing fields, such as radio astronomy, radar and sonar. |
| Tasks | Deblurring |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9665-deepwave-a-recurrent-neural-network-for-real-time-acoustic-imaging |
| http://papers.nips.cc/paper/9665-deepwave-a-recurrent-neural-network-for-real-time-acoustic-imaging.pdf | |
| PWC | https://paperswithcode.com/paper/deepwave-a-recurrent-neural-network-for-real |
| Repo | https://github.com/imagingofthings/DeepWave |
| Framework | none |
AGEM: Solving Linear Inverse Problems via Deep Priors and Sampling
| Title | AGEM: Solving Linear Inverse Problems via Deep Priors and Sampling |
| Authors | Bichuan Guo, Yuxing Han, Jiangtao Wen |
| Abstract | In this paper we propose to use a denoising autoencoder (DAE) prior to simultaneously solve a linear inverse problem and estimate its noise parameter. Existing DAE-based methods estimate the noise parameter empirically or treat it as a tunable hyper-parameter. We instead propose autoencoder guided EM, a probabilistically sound framework that performs Bayesian inference with intractable deep priors. We show that efficient posterior sampling from the DAE can be achieved via Metropolis-Hastings, which allows the Monte Carlo EM algorithm to be used. We demonstrate competitive results for signal denoising, image deblurring and image devignetting. Our method is an example of combining the representation power of deep learning with uncertainty quantification from Bayesian statistics. |
| Tasks | Bayesian Inference, Deblurring, Denoising |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8345-agem-solving-linear-inverse-problems-via-deep-priors-and-sampling |
| http://papers.nips.cc/paper/8345-agem-solving-linear-inverse-problems-via-deep-priors-and-sampling.pdf | |
| PWC | https://paperswithcode.com/paper/agem-solving-linear-inverse-problems-via-deep |
| Repo | https://github.com/gbc16/AGEM |
| Framework | pytorch |
Seeing Things from a Different Angle:Discovering Diverse Perspectives about Claims
| Title | Seeing Things from a Different Angle:Discovering Diverse Perspectives about Claims |
| Authors | Sihao Chen, Daniel Khashabi, Wenpeng Yin, Chris Callison-Burch, Dan Roth |
| Abstract | One key consequence of the information revolution is a significant increase and a contamination of our information supply. The practice of fact checking won{'}t suffice to eliminate the biases in text data we observe, as the degree of factuality alone does not determine whether biases exist in the spectrum of opinions visible to us. To better understand controversial issues, one needs to view them from a diverse yet comprehensive set of perspectives. For example, there are many ways to respond to a claim such as {``}animals should have lawful rights{''}, and these responses form a spectrum of perspectives, each with a stance relative to this claim and, ideally, with evidence supporting it. Inherently, this is a natural language understanding task, and we propose to address it as such. Specifically, we propose the task of substantiated perspective discovery where, given a claim, a system is expected to discover a diverse set of well-corroborated perspectives that take a stance with respect to the claim. Each perspective should be substantiated by evidence paragraphs which summarize pertinent results and facts. We construct PERSPECTRUM, a dataset of claims, perspectives and evidence, making use of online debate websites to create the initial data collection, and augmenting it using search engines in order to expand and diversify our dataset. We use crowd-sourcing to filter out noise and ensure high-quality data. Our dataset contains 1k claims, accompanied with pools of 10k and 8k perspective sentences and evidence paragraphs, respectively. We provide a thorough analysis of the dataset to highlight key underlying language understanding challenges, and show that human baselines across multiple subtasks far outperform ma-chine baselines built upon state-of-the-art NLP techniques. This poses a challenge and opportunity for the NLP community to address. | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1053/ |
| https://www.aclweb.org/anthology/N19-1053 | |
| PWC | https://paperswithcode.com/paper/seeing-things-from-a-different |
| Repo | https://github.com/CogComp/perspectrum |
| Framework | none |
Challenges and frontiers in abusive content detection
| Title | Challenges and frontiers in abusive content detection |
| Authors | Bertie Vidgen, Alex Harris, Dong Nguyen, Rebekah Tromble, Scott Hale, Helen Margetts |
| Abstract | Online abusive content detection is an inherently difficult task. It has received considerable attention from academia, particularly within the computational linguistics community, and performance appears to have improved as the field has matured. However, considerable challenges and unaddressed frontiers remain, spanning technical, social and ethical dimensions. These issues constrain the performance, efficiency and generalizability of abusive content detection systems. In this article we delineate and clarify the main challenges and frontiers in the field, critically evaluate their implications and discuss potential solutions. We also highlight ways in which social scientific insights can advance research. We discuss the lack of support given to researchers working with abusive content and provide guidelines for ethical research. |
| Tasks | Abuse Detection |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3509/ |
| https://www.aclweb.org/anthology/W19-3509 | |
| PWC | https://paperswithcode.com/paper/challenges-and-frontiers-in-abusive-content |
| Repo | https://github.com/bvidgen/Challenges-and-frontiers-in-abusive-content-detection |
| Framework | none |
Compositional De-Attention Networks
| Title | Compositional De-Attention Networks |
| Authors | Yi Tay, Anh Tuan Luu, Aston Zhang, Shuohang Wang, Siu Cheung Hui |
| Abstract | Attentional models are distinctly characterized by their ability to learn relative importance, i.e., assigning a different weight to input values. This paper proposes a new quasi-attention that is compositional in nature, i.e., learning whether to \textit{add}, \textit{subtract} or \textit{nullify} a certain vector when learning representations. This is strongly contrasted with vanilla attention, which simply re-weights input tokens. Our proposed \textit{Compositional De-Attention} (CoDA) is fundamentally built upon the intuition of both similarity and dissimilarity (negative affinity) when computing affinity scores, benefiting from a greater extent of expressiveness. We evaluate CoDA on six NLP tasks, i.e. open domain question answering, retrieval/ranking, natural language inference, machine translation, sentiment analysis and text2code generation. We obtain promising experimental results, achieving state-of-the-art performance on several tasks/datasets. |
| Tasks | Machine Translation, Natural Language Inference, Open-Domain Question Answering, Question Answering, Sentiment Analysis |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8845-compositional-de-attention-networks |
| http://papers.nips.cc/paper/8845-compositional-de-attention-networks.pdf | |
| PWC | https://paperswithcode.com/paper/compositional-de-attention-networks |
| Repo | https://github.com/vanzytay/NeurIPS2019_CODA |
| Framework | none |
MABWiser: A Parallelizable Contextual Multi-Armed Bandit Library for Python
| Title | MABWiser: A Parallelizable Contextual Multi-Armed Bandit Library for Python |
| Authors | Emily Strong, Bernard Kleynhans, Serdar Kadioglu |
| Abstract | Contextual multi-armed bandit algorithms serve as an effective technique to address online sequential decision-making problems. Despite their popularity, when it comes to off-the-shelf tools the library support remains limited, in particular for the Python technology stack. To fill this gap, in this paper we present a system that provides context-free, parametric and nonparametric contextual multi-armed bandit models. The available bandit policies accommodate both batch and online learning. The MABWISER system is implemented as an open-source Python library. Our design enables built-in parallelization to speed up training and test components for scalability while ensuring the reproducibility of results. We present a running example to highlight the user-friendly nature of the public interface and discuss the simulation capability of the library for hyperparameter tuning and rapid experimentation. |
| Tasks | Decision Making |
| Published | 2019-10-04 |
| URL | http://www.ictai2019.org/ |
| http://www.ictai2019.org/ | |
| PWC | https://paperswithcode.com/paper/mabwiser-a-parallelizable-contextual-multi |
| Repo | https://github.com/fmr-llc/mabwiser |
| Framework | none |
First Steps towards Building a Medical Lexicon for Spanish with Linguistic and Semantic Information
| Title | First Steps towards Building a Medical Lexicon for Spanish with Linguistic and Semantic Information |
| Authors | Leonardo Campillos-Llanos |
| Abstract | We report the work-in-progress of collecting MedLexSp, an unified medical lexicon for the Spanish language, featuring terms and inflected word forms mapped to Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs), semantic types and groups. First, we leveraged a list of term lemmas and forms from a previous project, and mapped them to UMLS terms and CUIs. To enrich the lexicon, we used both domain-corpora (e.g. Summaries of Product Characteristics and MedlinePlus) and natural language processing techniques such as string distance methods or generation of syntactic variants of multi-word terms. We also added term variants by mapping their CUIs to missing items available in the Spanish versions of standard thesauri (e.g. Medical Subject Headings and World Health Organization Adverse Drug Reactions terminology). We enhanced the vocabulary coverage by gathering missing terms from resources such as the Anatomical Therapeutical Classification, the National Cancer Institute (NCI) Dictionary of Cancer Terms, OrphaData, or the Nomencl{'a}tor de Prescripci{'o}n for drug names. Part-of-Speech information is being included in the lexicon, and the current version amounts up to 76 454 lemmas and 203 043 inflected forms (including conjugated verbs, number and gender variants), corresponding to 30 647 UMLS CUIs. MedLexSp is distributed freely for research purposes. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5017/ |
| https://www.aclweb.org/anthology/W19-5017 | |
| PWC | https://paperswithcode.com/paper/first-steps-towards-building-a-medical |
| Repo | https://github.com/lcampillos/bionlp2019 |
| Framework | none |
Adversarial Defense via Learning to Generate Diverse Attacks
| Title | Adversarial Defense via Learning to Generate Diverse Attacks |
| Authors | Yunseok Jang, Tianchen Zhao, Seunghoon Hong, Honglak Lee |
| Abstract | With the remarkable success of deep learning, Deep Neural Networks (DNNs) have been applied as dominant tools to various machine learning domains. Despite this success, however, it has been found that DNNs are surprisingly vulnerable to malicious attacks; adding a small, perceptually indistinguishable perturbations to the data can easily degrade classification performance. Adversarial training is an effective defense strategy to train a robust classifier. In this work, we propose to utilize the generator to learn how to create adversarial examples. Unlike the existing approaches that create a one-shot perturbation by a deterministic generator, we propose a recursive and stochastic generator that produces much stronger and diverse perturbations that comprehensively reveal the vulnerability of the target classifier. Our experiment results on MNIST and CIFAR-10 datasets show that the classifier adversarially trained with our method yields more robust performance over various white-box and black-box attacks. |
| Tasks | Adversarial Defense |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Jang_Adversarial_Defense_via_Learning_to_Generate_Diverse_Attacks_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Jang_Adversarial_Defense_via_Learning_to_Generate_Diverse_Attacks_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-defense-via-learning-to-generate |
| Repo | https://github.com/YunseokJANG/l2l-da |
| Framework | pytorch |
Cost Effective Active Search
| Title | Cost Effective Active Search |
| Authors | Shali Jiang, Roman Garnett, Benjamin Moseley |
| Abstract | We study a special paradigm of active learning, called cost effective active search, where the goal is to find a given number of positive points from a large unlabeled pool with minimum labeling cost. Most existing methods solve this problem heuristically, and few theoretical results have been established. We adopt a principled Bayesian approach for the first time. We first derive the Bayesian optimal policy and establish a strong hardness result: the optimal policy is hard to approximate, with the best-possible approximation ratio lower bounded by $\Omega(n^{0.16})$. We then propose an efficient and nonmyopic policy using the negative Poisson binomial distribution. We propose simple and fast approximations for computing its expectation, which serves as an essential role in our proposed policy. We conduct comprehensive experiments on various domains such as drug and materials discovery, and demonstrate that our proposed search procedure is superior to the widely used greedy baseline. |
| Tasks | Active Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8734-cost-effective-active-search |
| http://papers.nips.cc/paper/8734-cost-effective-active-search.pdf | |
| PWC | https://paperswithcode.com/paper/cost-effective-active-search |
| Repo | https://github.com/shalijiang/efficient_nonmyopic_active_search |
| Framework | none |
Second-Order Attention Network for Single Image Super-Resolution
| Title | Second-Order Attention Network for Single Image Super-Resolution |
| Authors | Tao Dai, Jianrui Cai, Yongbing Zhang, Shu-Tao Xia, Lei Zhang |
| Abstract | Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and obtained remarkable performance. However, most of the existing CNN-based SISR methods mainly focus on wider or deeper architecture design, neglecting to explore the feature correlations of intermediate layers, hence hindering the representational power of CNNs. To address this issue, in this paper, we propose a second-order attention network (SAN) for more powerful feature expression and feature correlation learning. Specifically, a novel train- able second-order channel attention (SOCA) module is developed to adaptively rescale the channel-wise features by using second-order feature statistics for more discriminative representations. Furthermore, we present a non-locally enhanced residual group (NLRG) structure, which not only incorporates non-local operations to capture long-distance spatial contextual information, but also contains repeated local-source residual attention groups (LSRAG) to learn increasingly abstract feature representations. Experimental results demonstrate the superiority of our SAN network over state-of-the-art SISR methods in terms of both quantitative metrics and visual quality. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Dai_Second-Order_Attention_Network_for_Single_Image_Super-Resolution_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Dai_Second-Order_Attention_Network_for_Single_Image_Super-Resolution_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/second-order-attention-network-for-single |
| Repo | https://github.com/daitao/SAN |
| Framework | pytorch |
On Learning Symmetric Locomotion
| Title | On Learning Symmetric Locomotion |
| Authors | Farzad Abdolhosseini, Hung Yu Ling, Zhaoming Xie, Xue Bin Peng, Michiel van de Panne |
| Abstract | Human and animal gaits are often symmetric in nature, which points to the use of motion symmetry as a potentially useful source of structure that can be exploited for learning. By encouraging symmetric motion, the learning may be faster, converge to more efficient solutions, and be more aesthetically pleasing. We describe, compare, and evaluate four practical methods for encouraging motion symmetry. These are implemented via particular choices of structure for the policy network, data duplication, or via the loss function. We experimentally evaluate the methods in terms of learning performance and achieved symmetry, and provide summary guidelines for the choice of symmetry method. We further describe some practical and conceptual issues that arise. Because similar implementation choices exist for other types of inductive biases, the insights gained may also be relevant to other learning problems with applicable symmetry abstractions. |
| Tasks | |
| Published | 2019-10-28 |
| URL | https://www.cs.ubc.ca/~van/papers/2019-MIG-symmetry/index.html |
| https://www.cs.ubc.ca/~van/papers/2019-MIG-symmetry/2019-MIG-symmetry.pdf | |
| PWC | https://paperswithcode.com/paper/on-learning-symmetric-locomotion |
| Repo | https://github.com/UBCMOCCA/SymmetricRL |
| Framework | pytorch |
