January 27, 2020

3123 words 15 mins read

Paper Group ANR 1170

Multi-label Categorization of Accounts of Sexism using a Neural Framework. Exploring Computational User Models for Agent Policy Summarization. Deep Convolutional Networks in System Identification. Forecasting Mobile Traffic with Spatiotemporal correlation using Deep Regression. Human Action Recognition with Deep Temporal Pyramids. Robust Classifica …

Multi-label Categorization of Accounts of Sexism using a Neural Framework


Title	Multi-label Categorization of Accounts of Sexism using a Neural Framework
Authors	Pulkit Parikh, Harika Abburi, Pinkesh Badjatiya, Radhika Krishnan, Niyati Chhaya, Manish Gupta, Vasudeva Varma
Abstract	Sexism, an injustice that subjects women and girls to enormous suffering, manifests in blatant as well as subtle ways. In the wake of growing documentation of experiences of sexism on the web, the automatic categorization of accounts of sexism has the potential to assist social scientists and policy makers in studying and countering sexism better. The existing work on sexism classification, which is different from sexism detection, has certain limitations in terms of the categories of sexism used and/or whether they can co-occur. To the best of our knowledge, this is the first work on the multi-label classification of sexism of any kind(s), and we contribute the largest dataset for sexism categorization. We develop a neural solution for this multi-label classification that can combine sentence representations obtained using models such as BERT with distributional and linguistic word embeddings using a flexible, hierarchical architecture involving recurrent components and optional convolutional ones. Further, we leverage unlabeled accounts of sexism to infuse domain-specific elements into our framework. The best proposed method outperforms several deep learning as well as traditional machine learning baselines by an appreciable margin.
Tasks	Multi-Label Classification, Word Embeddings
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04602v4
PDF	https://arxiv.org/pdf/1910.04602v4.pdf
PWC	https://paperswithcode.com/paper/multi-label-categorization-of-accounts-of
Repo
Framework

Exploring Computational User Models for Agent Policy Summarization


Title	Exploring Computational User Models for Agent Policy Summarization
Authors	Isaac Lage, Daphna Lifschitz, Finale Doshi-Velez, Ofra Amir
Abstract	AI agents are being developed to support high stakes decision-making processes from driving cars to prescribing drugs, making it increasingly important for human users to understand their behavior. Policy summarization methods aim to convey strengths and weaknesses of such agents by demonstrating their behavior in a subset of informative states. Some policy summarization methods extract a summary that optimizes the ability to reconstruct the agent’s policy under the assumption that users will deploy inverse reinforcement learning. In this paper, we explore the use of different models for extracting summaries. We introduce an imitation learning-based approach to policy summarization; we demonstrate through computational simulations that a mismatch between the model used to extract a summary and the model used to reconstruct the policy results in worse reconstruction quality; and we demonstrate through a human-subject study that people use different models to reconstruct policies in different contexts, and that matching the summary extraction model to these can improve performance. Together, our results suggest that it is important to carefully consider user models in policy summarization.
Tasks	Decision Making, Imitation Learning
Published	2019-05-30
URL	https://arxiv.org/abs/1905.13271v1
PDF	https://arxiv.org/pdf/1905.13271v1.pdf
PWC	https://paperswithcode.com/paper/exploring-computational-user-models-for-agent
Repo
Framework

Deep Convolutional Networks in System Identification


Title	Deep Convolutional Networks in System Identification
Authors	Carl Andersson, Antônio H. Ribeiro, Koen Tiels, Niklas Wahlström, Thomas B. Schön
Abstract	Recent developments within deep learning are relevant for nonlinear system identification problems. In this paper, we establish connections between the deep learning and the system identification communities. It has recently been shown that convolutional architectures are at least as capable as recurrent architectures when it comes to sequence modeling tasks. Inspired by these results we explore the explicit relationships between the recently proposed temporal convolutional network (TCN) and two classic system identification model structures; Volterra series and block-oriented models. We end the paper with an experimental study where we provide results on two real-world problems, the well-known Silverbox dataset and a newer dataset originating from ground vibration experiments on an F-16 fighter aircraft.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1909.01730v2
PDF	https://arxiv.org/pdf/1909.01730v2.pdf
PWC	https://paperswithcode.com/paper/deep-convolutional-networks-in-system
Repo
Framework

Forecasting Mobile Traffic with Spatiotemporal correlation using Deep Regression


Title	Forecasting Mobile Traffic with Spatiotemporal correlation using Deep Regression
Authors	Giulio Siracusano, Aurelio La Corte
Abstract	The concept of mobility prediction represents one of the key enablers for an efficient management of future cellular networks, which tend to be progressively more elaborate and dense due to the aggregation of multiple technologies. In this letter we aim to investigate the problem of cellular traffic prediction over a metropolitan area and propose a deep regression (DR) approach to model its complex spatio-temporal dynamics. DR is instrumental in capturing multi-scale and multi-domain dependences of mobile data by solving an image-to-image regression problem. A parametric relationship between input and expected output is defined and grid search is put in place to isolate and optimize performance. Experimental results confirm that the proposed method achieves a lower prediction error against stateof-the-art algorithms. We validate forecasting performance and stability by using a large public dataset of a European Provider.
Tasks	Traffic Prediction
Published	2019-07-25
URL	https://arxiv.org/abs/1907.10865v1
PDF	https://arxiv.org/pdf/1907.10865v1.pdf
PWC	https://paperswithcode.com/paper/forecasting-mobile-traffic-with
Repo
Framework

Human Action Recognition with Deep Temporal Pyramids


Title	Human Action Recognition with Deep Temporal Pyramids
Authors	Ahmed Mazari, Hichem Sahbi
Abstract	Deep convolutional neural networks (CNNs) are nowadays achieving significant leaps in different pattern recognition tasks including action recognition. Current CNNs are increasingly deeper, data-hungrier and this makes their success tributary of the abundance of labeled training data. CNNs also rely on max/average pooling which reduces dimensionality of output layers and hence attenuates their sensitivity to the availability of labeled data. However, this process may dilute the information of upstream convolutional layers and thereby affect the discrimination power of the trained representations, especially when the learned categories are fine-grained. In this paper, we introduce a novel hierarchical aggregation design, for final pooling, that controls granularity of the learned representations w.r.t the actual granularity of action categories. Our solution is based on a tree-structured temporal pyramid that aggregates outputs of CNNs at different levels. Top levels of this hierarchy are dedicated to coarse categories while deep levels are more suitable to fine-grained ones. The design of our temporal pyramid is based on solving a constrained minimization problem whose solution corresponds to the distribution of weights of different representations in the temporal pyramid. Experiments conducted using the challenging UCF101 database show the relevance of our hierarchical design w.r.t other related methods.
Tasks	Temporal Action Localization
Published	2019-05-02
URL	https://arxiv.org/abs/1905.00745v1
PDF	https://arxiv.org/pdf/1905.00745v1.pdf
PWC	https://paperswithcode.com/paper/human-action-recognition-with-deep-temporal
Repo
Framework

Robust Classification using Robust Feature Augmentation


Title	Robust Classification using Robust Feature Augmentation
Authors	Kevin Eykholt, Swati Gupta, Atul Prakash, Amir Rahmati, Pratik Vaishnavi, Haizhong Zheng
Abstract	Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image. In this work, we propose shock absorbing robust features such as binarization, e.g., rounding, and group extraction, e.g., color or shape, to augment the classification pipeline, resulting in more robust classifiers. Experimentally, we show that augmenting ML models with these techniques leads to improved overall robustness on adversarial inputs as well as significant improvements in training time. On the MNIST dataset, we achieved 14x speedup in training time to obtain 90% adversarial accuracy com-pared to the state-of-the-art adversarial training method of Madry et al., as well as retained higher adversarial accuracy over a broader range of attacks. We also find robustness improvements on traffic sign classification using robust feature augmentation. Finally, we give theoretical insights for why one can expect robust feature augmentation to reduce adversarial input space
Tasks	Image Classification
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10904v3
PDF	https://arxiv.org/pdf/1905.10904v3.pdf
PWC	https://paperswithcode.com/paper/robust-classification-using-robust-feature
Repo
Framework

Adversarial Imitation Learning from Incomplete Demonstrations


Title	Adversarial Imitation Learning from Incomplete Demonstrations
Authors	Mingfei Sun, Xiaojuan Ma
Abstract	Imitation learning targets deriving a mapping from states to actions, a.k.a. policy, from expert demonstrations. Existing methods for imitation learning typically require any actions in the demonstrations to be fully available, which is hard to ensure in real applications. Though algorithms for learning with unobservable actions have been proposed, they focus solely on state information and overlook the fact that the action sequence could still be partially available and provide useful information for policy deriving. In this paper, we propose a novel algorithm called Action-Guided Adversarial Imitation Learning (AGAIL) that learns a policy from demonstrations with incomplete action sequences, i.e., incomplete demonstrations. The core idea of AGAIL is to separate demonstrations into state and action trajectories, and train a policy with state trajectories while using actions as auxiliary information to guide the training whenever applicable. Built upon the Generative Adversarial Imitation Learning, AGAIL has three components: a generator, a discriminator, and a guide. The generator learns a policy with rewards provided by the discriminator, which tries to distinguish state distributions between demonstrations and samples generated by the policy. The guide provides additional rewards to the generator when demonstrated actions for specific states are available. We compare AGAIL to other methods on benchmark tasks and show that AGAIL consistently delivers comparable performance to the state-of-the-art methods even when the action sequence in demonstrations is only partially available.
Tasks	Imitation Learning
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12310v3
PDF	https://arxiv.org/pdf/1905.12310v3.pdf
PWC	https://paperswithcode.com/paper/adversarial-imitation-learning-from
Repo
Framework

A mixture of experts model for predicting persistent weather patterns


Title	A mixture of experts model for predicting persistent weather patterns
Authors	Maria Perez-Ortiz, Pedro A. Gutierrez, Peter Tino, Carlos Casanova-Mateo, Sancho Salcedo-Sanz
Abstract	Weather and atmospheric patterns are often persistent. The simplest weather forecasting method is the so-called persistence model, which assumes that the future state of a system will be similar (or equal) to the present state. Machine learning (ML) models are widely used in different weather forecasting applications, but they need to be compared to the persistence model to analyse whether they provide a competitive solution to the problem at hand. In this paper, we devise a new model for predicting low-visibility in airports using the concepts of mixture of experts. Visibility level is coded as two different ordered categorical variables: cloud height and runway visual height. The underlying system in this application is stagnant approximately in 90% of the cases, and standard ML models fail to improve on the performance of the persistence model. Because of this, instead of trying to simply beat the persistence model using ML, we use this persistence as a baseline and learn an ordinal neural network model that refines its results by focusing on learning weather fluctuations. The results show that the proposal outperforms persistence and other ordinal autoregressive models, especially for longer time horizon predictions and for the runway visual height variable.
Tasks	Weather Forecasting
Published	2019-03-24
URL	http://arxiv.org/abs/1903.10012v1
PDF	http://arxiv.org/pdf/1903.10012v1.pdf
PWC	https://paperswithcode.com/paper/a-mixture-of-experts-model-for-predicting
Repo
Framework

Measuring the Business Value of Recommender Systems


Title	Measuring the Business Value of Recommender Systems
Authors	Dietmar Jannach, Michael Jugovac
Abstract	Recommender Systems are nowadays successfully used by all major web sites (from e-commerce to social media) to filter content and make suggestions in a personalized way. Academic research largely focuses on the value of recommenders for consumers, e.g., in terms of reduced information overload. To what extent and in which ways recommender systems create business value is, however, much less clear, and the literature on the topic is scattered. In this research commentary, we review existing publications on field tests of recommender systems and report which business-related performance measures were used in such real-world deployments. We summarize common challenges of measuring the business value in practice and critically discuss the value of algorithmic improvements and offline experiments as commonly done in academic environments. Overall, our review indicates that various open questions remain both regarding the realistic quantification of the business effects of recommenders and the performance assessment of recommendation algorithms in academia.
Tasks	Recommendation Systems
Published	2019-08-22
URL	https://arxiv.org/abs/1908.08328v3
PDF	https://arxiv.org/pdf/1908.08328v3.pdf
PWC	https://paperswithcode.com/paper/measuring-the-business-value-of-recommender
Repo
Framework

A Survey of Reinforcement Learning Informed by Natural Language


Title	A Survey of Reinforcement Learning Informed by Natural Language
Authors	Jelena Luketina, Nantas Nardelli, Gregory Farquhar, Jakob Foerster, Jacob Andreas, Edward Grefenstette, Shimon Whiteson, Tim Rocktäschel
Abstract	To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation learning for language make it possible to build models that acquire world knowledge from text corpora and integrate this knowledge into downstream decision making problems. We thus argue that the time is right to investigate a tight integration of natural language understanding into RL in particular. We survey the state of the field, including work on instruction following, text games, and learning from textual domain knowledge. Finally, we call for the development of new environments as well as further investigation into the potential uses of recent Natural Language Processing (NLP) techniques for such tasks.
Tasks	Decision Making, Representation Learning
Published	2019-06-10
URL	https://arxiv.org/abs/1906.03926v1
PDF	https://arxiv.org/pdf/1906.03926v1.pdf
PWC	https://paperswithcode.com/paper/a-survey-of-reinforcement-learning-informed
Repo
Framework

Contextual Minimum-Norm Estimates (CMNE): A Deep Learning Method for Source Estimation in Neuronal Networks


Title	Contextual Minimum-Norm Estimates (CMNE): A Deep Learning Method for Source Estimation in Neuronal Networks
Authors	Christoph Dinh, John GW Samuelsson, Alexander Hunold, Matti S Hämäläinen, Sheraz Khan
Abstract	Magnetoencephalography (MEG) and Electroencephalography (EEG) source estimates have thus far mostly been derived sample by sample, i.e., independent of each other in time. However, neuronal assemblies are heavily interconnected, constraining the temporal evolution of neural activity in space as detected by MEG and EEG. The observed neural currents are thus highly context dependent. Here, a new method is presented which integrates predictive deep learning networks with the Minimum-Norm Estimates (MNE) approach. Specifically, we employ Long Short-Term Memory (LSTM) networks, a type of recurrent neural network, for predicting brain activity. Because we use past activity (context) in the estimation, we call our method Contextual MNE (CMNE). We demonstrate that these contextual algorithms can be used for predicting activity based on previous brain states and when used in conjunction with MNE, they lead to more accurate source estimation. To evaluate the performance of CMNE, it was tested on simulated and experimental data from human auditory evoked response experiments.
Tasks	EEG
Published	2019-09-05
URL	https://arxiv.org/abs/1909.02636v1
PDF	https://arxiv.org/pdf/1909.02636v1.pdf
PWC	https://paperswithcode.com/paper/contextual-minimum-norm-estimates-cmne-a-deep
Repo
Framework

Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention


Title	Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention
Authors	Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Fatemeh Sadat Saleh, Hongdong Li, Stephen Gould
Abstract	This paper studies the problem of temporal moment localization in a long untrimmed video using natural language as the query. Given an untrimmed video and a sentence as the query, the goal is to determine the starting, and the ending, of the relevant visual moment in the video, that corresponds to the query sentence. While previous works have tackled this task by a propose-and-rank approach, we introduce a more efficient, end-to-end trainable, and {\em proposal-free approach} that relies on three key components: a dynamic filter to transfer language information to the visual domain, a new loss function to guide our model to attend the most relevant parts of the video, and soft labels to model annotation uncertainty. We evaluate our method on two benchmark datasets, Charades-STA and ActivityNet-Captions. Experimental results show that our approach outperforms state-of-the-art methods on both datasets.
Tasks
Published	2019-08-20
URL	https://arxiv.org/abs/1908.07236v2
PDF	https://arxiv.org/pdf/1908.07236v2.pdf
PWC	https://paperswithcode.com/paper/proposal-free-temporal-moment-localization-of
Repo
Framework

Learning Category Correlations for Multi-label Image Recognition with Graph Networks


Title	Learning Category Correlations for Multi-label Image Recognition with Graph Networks
Authors	Qing Li, Xiaojiang Peng, Yu Qiao, Qiang Peng
Abstract	Multi-label image recognition is a task that predicts a set of object labels in an image. As the objects co-occur in the physical world, it is desirable to model label dependencies. Previous existing methods resort to either recurrent networks or pre-defined label correlation graphs for this purpose. In this paper, instead of using a pre-defined graph which is inflexible and may be sub-optimal for multi-label classification, we propose the A-GCN, which leverages the popular Graph Convolutional Networks with an Adaptive label correlation graph to model label dependencies. Specifically, we introduce a plug-and-play Label Graph (LG) module to learn label correlations with word embeddings, and then utilize traditional GCN to map this graph into label-dependent object classifiers which are further applied to image features. The basic LG module incorporates two 1x1 convolutional layers and uses the dot product to generate label graphs. In addition, we propose a sparse correlation constraint to enhance the LG module and also explore different LG architectures. We validate our method on two diverse multi-label datasets: MS-COCO and Fashion550K. Experimental results show that our A-GCN significantly improves baseline methods and achieves performance superior or comparable to the state of the art.
Tasks	Multi-Label Classification, Word Embeddings
Published	2019-09-28
URL	https://arxiv.org/abs/1909.13005v1
PDF	https://arxiv.org/pdf/1909.13005v1.pdf
PWC	https://paperswithcode.com/paper/learning-category-correlations-for-multi
Repo
Framework

Interrogating the Explanatory Power of Attention in Neural Machine Translation


Title	Interrogating the Explanatory Power of Attention in Neural Machine Translation
Authors	Pooya Moradi, Nishant Kambhatla, Anoop Sarkar
Abstract	Attention models have become a crucial component in neural machine translation (NMT). They are often implicitly or explicitly used to justify the model’s decision in generating a specific token but it has not yet been rigorously established to what extent attention is a reliable source of information in NMT. To evaluate the explanatory power of attention for NMT, we examine the possibility of yielding the same prediction but with counterfactual attention models that modify crucial aspects of the trained attention model. Using these counterfactual attention mechanisms we assess the extent to which they still preserve the generation of function and content words in the translation process. Compared to a state of the art attention model, our counterfactual attention models produce 68% of function words and 21% of content words in our German-English dataset. Our experiments demonstrate that attention models by themselves cannot reliably explain the decisions made by a NMT model.
Tasks	Machine Translation
Published	2019-09-30
URL	https://arxiv.org/abs/1910.00139v1
PDF	https://arxiv.org/pdf/1910.00139v1.pdf
PWC	https://paperswithcode.com/paper/interrogating-the-explanatory-power-of
Repo
Framework


Title	Privacy-preserving data sharing via probabilistic modelling
Authors	Joonas Jälkö, Eemil Lagerspetz, Jari Haukka, Sasu Tarkoma, Samuel Kaski, Antti Honkela
Abstract	Differential privacy allows quantifying privacy loss from computations on sensitive personal data. This loss grows with the number of accesses to the data, making it hard to open the use of such data while respecting privacy. To avoid this limitation, we propose privacy-preserving release of a synthetic version of a data set, which can be used for an unlimited number of analyses with any methods, without affecting the privacy guarantees. The synthetic data generation is based on differentially private learning of a generative probabilistic model which can capture the probability distribution of the original data. We demonstrate empirically that we can reliably reproduce statistical discoveries from the synthetic data. We expect the method to have broad use in sharing anonymized versions of key data sets for research.
Tasks	Synthetic Data Generation
Published	2019-12-10
URL	https://arxiv.org/abs/1912.04439v2
PDF	https://arxiv.org/pdf/1912.04439v2.pdf
PWC	https://paperswithcode.com/paper/privacy-preserving-data-sharing-via
Repo
Framework