January 25, 2020

3481 words 17 mins read

Paper Group ANR 1770

Spectrum-enhanced Pairwise Learning to Rank. Minimizing Time-to-Rank: A Learning and Recommendation Approach. An Approximate Bayesian Approach to Surprise-Based Learning. Learning Bilingual Word Embeddings Using Lexical Definitions. Improving Relation Extraction with Knowledge-attention. PH-GCN: Person Re-identification with Part-based Hierarchical …

Spectrum-enhanced Pairwise Learning to Rank


Title	Spectrum-enhanced Pairwise Learning to Rank
Authors	Wenhui Yu, Zheng Qin
Abstract	To enhance the performance of the recommender system, side information is extensively explored with various features (e.g., visual features and textual features). However, there are some demerits of side information: (1) the extra data is not always available in all recommendation tasks; (2) it is only for items, there is seldom high-level feature describing users. To address these gaps, we introduce the spectral features extracted from two hypergraph structures of the purchase records. Spectral features describe the \textit{similarity} of users/items in the graph space, which is critical for recommendation. We leverage spectral features to model the users’ preference and items’ properties by incorporating them into a Matrix Factorization (MF) model. In addition to modeling, we also use spectral features to optimize. Bayesian Personalized Ranking (BPR) is extensively leveraged to optimize models in implicit feedback data. However, in BPR, all missing values are regarded as negative samples equally while many of them are indeed unseen positive ones. We enrich the positive samples by calculating the similarity among users/items by the spectral features. The key ideas are: (1) similar users shall have similar preference on the same item; (2) a user shall have similar perception on similar items. Extensive experiments on two real-world datasets demonstrate the usefulness of the spectral features and the effectiveness of our spectrum-enhanced pairwise optimization. Our models outperform several state-of-the-art models significantly.
Tasks	Learning-To-Rank, Recommendation Systems
Published	2019-05-02
URL	https://arxiv.org/abs/1905.00805v1
PDF	https://arxiv.org/pdf/1905.00805v1.pdf
PWC	https://paperswithcode.com/paper/spectrum-enhanced-pairwise-learning-to-rank
Repo
Framework

Minimizing Time-to-Rank: A Learning and Recommendation Approach


Title	Minimizing Time-to-Rank: A Learning and Recommendation Approach
Authors	Haoming Li, Sujoy Sikdar, Rohit Vaish, Junming Wang, Lirong Xia, Chaonan Ye
Abstract	Consider the following problem faced by an online voting platform: A user is provided with a list of alternatives, and is asked to rank them in order of preference using only drag-and-drop operations. The platform’s goal is to recommend an initial ranking that minimizes the time spent by the user in arriving at her desired ranking. We develop the first optimization framework to address this problem, and make theoretical as well as practical contributions. On the practical side, our experiments on Amazon Mechanical Turk provide two interesting insights about user behavior: First, that users’ ranking strategies closely resemble selection or insertion sort, and second, that the time taken for a drag-and-drop operation depends linearly on the number of positions moved. These insights directly motivate our theoretical model of the optimization problem. We show that computing an optimal recommendation is NP-hard, and provide exact and approximation algorithms for a variety of special cases of the problem. Experimental evaluation on MTurk shows that, compared to a random recommendation strategy, the proposed approach reduces the (average) time-to-rank by up to 50%.
Tasks
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11984v1
PDF	https://arxiv.org/pdf/1905.11984v1.pdf
PWC	https://paperswithcode.com/paper/minimizing-time-to-rank-a-learning-and
Repo
Framework

An Approximate Bayesian Approach to Surprise-Based Learning


Title	An Approximate Bayesian Approach to Surprise-Based Learning
Authors	Vasiliki Liakoni, Alireza Modirshanechi, Wulfram Gerstner, Johanni Brea
Abstract	Surprise-based learning allows agents to rapidly adapt to non-stationary stochastic environments characterized by stationary periods separated by sudden changes. We show that exact Bayesian inference in a hierarchical model gives rise to a surprise-modulated trade-off between forgetting old observations and integrating them with the new ones. The modulation depends on a probability ratio, called the “Bayes Factor Surprise” that tests the prior belief against the current belief. We demonstrate that in several existing approximate algorithms the Bayes Factor Surprise modulates the rate of adaptation to new observations. We derive three novel surprised-based algorithms, one in the family of particle filters, one in the family of variational learning, and the other in the family of message passing, that are biologically plausible, have constant scaling in observation sequence length and particularly simple update dynamics for any distribution in the exponential family. Empirical results show that these surprise-based algorithms estimate parameters better than alternative approximate approaches and reach levels of performance comparable to computationally more expensive algorithms. The Bayes Factor Surprise is related to but different from Shannon Surprise. In two hypothetical experiments, we make testable predictions for physiological or behavioral indicators that dissociate the Bayes Factor Surprise from Shannon Surprise. The theoretical insight of casting various approaches as surprise-based learning, as well as the proposed online algorithms, may be applied to the analysis of animal and human behavior, and to reinforcement learning in non-stationary environments.
Tasks	Bayesian Inference
Published	2019-07-05
URL	https://arxiv.org/abs/1907.02936v2
PDF	https://arxiv.org/pdf/1907.02936v2.pdf
PWC	https://paperswithcode.com/paper/an-approximate-bayesian-approach-to-surprise
Repo
Framework

Learning Bilingual Word Embeddings Using Lexical Definitions


Title	Learning Bilingual Word Embeddings Using Lexical Definitions
Authors	Weijia Shi, Muhao Chen, Yingtao Tian, Kai-Wei Chang
Abstract	Bilingual word embeddings, which representlexicons of different languages in a shared em-bedding space, are essential for supporting se-mantic and knowledge transfers in a variety ofcross-lingual NLP tasks. Existing approachesto training bilingual word embeddings requireoften require pre-defined seed lexicons that areexpensive to obtain, or parallel sentences thatcomprise coarse and noisy alignment. In con-trast, we propose BilLex that leverages pub-licly available lexical definitions for bilingualword embedding learning. Without the needof predefined seed lexicons, BilLex comprisesa novel word pairing strategy to automati-cally identify and propagate the precise fine-grained word alignment from lexical defini-tions. We evaluate BilLex in word-level andsentence-level translation tasks, which seek tofind the cross-lingual counterparts of wordsand sentences respectively.BilLex signifi-cantly outperforms previous embedding meth-ods on both tasks.
Tasks	Word Alignment, Word Embeddings
Published	2019-06-21
URL	https://arxiv.org/abs/1906.08939v1
PDF	https://arxiv.org/pdf/1906.08939v1.pdf
PWC	https://paperswithcode.com/paper/learning-bilingual-word-embeddings-using
Repo
Framework

Improving Relation Extraction with Knowledge-attention


Title	Improving Relation Extraction with Knowledge-attention
Authors	Pengfei Li, Kezhi Mao, Xuefeng Yang, Qi Li
Abstract	While attention mechanisms have been proven to be effective in many NLP tasks, majority of them are data-driven. We propose a novel knowledge-attention encoder which incorporates prior knowledge from external lexical resources into deep neural networks for relation extraction task. Furthermore, we present three effective ways of integrating knowledge-attention with self-attention to maximize the utilization of both knowledge and data. The proposed relation extraction system is end-to-end and fully attention-based. Experiment results show that the proposed knowledge-attention mechanism has complementary strengths with self-attention, and our integrated models outperform existing CNN, RNN, and self-attention based models. State-of-the-art performance is achieved on TACRED, a complex and large-scale relation extraction dataset.
Tasks	Relation Extraction
Published	2019-10-07
URL	https://arxiv.org/abs/1910.02724v2
PDF	https://arxiv.org/pdf/1910.02724v2.pdf
PWC	https://paperswithcode.com/paper/improving-relation-extraction-with-knowledge
Repo
Framework

PH-GCN: Person Re-identification with Part-based Hierarchical Graph Convolutional Network


Title	PH-GCN: Person Re-identification with Part-based Hierarchical Graph Convolutional Network
Authors	Bo Jiang, Xixi Wang, Bin Luo
Abstract	The person re-identification (Re-ID) task requires to robustly extract feature representations for person images. Recently, part-based representation models have been widely studied for extracting the more compact and robust feature representations for person images to improve person Re-ID results. However, existing part-based representation models mostly extract the features of different parts independently which ignore the relationship information between different parts. To overcome this limitation, in this paper we propose a novel deep learning framework, named Part-based Hierarchical Graph Convolutional Network (PH-GCN) for person Re-ID problem. Given a person image, PH-GCN first constructs a hierarchical graph to represent the pairwise relationships among different parts. Then, both local and global feature learning are performed by the messages passing in PH-GCN, which takes other nodes information into account for part feature representation. Finally, a perceptron layer is adopted for the final person part label prediction and re-identification. The proposed framework provides a general solution that integrates local, global and structural feature learning simultaneously in a unified end-to-end network. Extensive experiments on several benchmark datasets demonstrate the effectiveness of the proposed PH-GCN based Re-ID approach.
Tasks	Person Re-Identification
Published	2019-07-20
URL	https://arxiv.org/abs/1907.08822v1
PDF	https://arxiv.org/pdf/1907.08822v1.pdf
PWC	https://paperswithcode.com/paper/ph-gcn-person-re-identification-with-part
Repo
Framework

PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph


Title	PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph
Authors	Yikang Li, Tao Ma, Yeqi Bai, Nan Duan, Sining Wei, Xiaogang Wang
Abstract	Despite some exciting progress on high-quality image generation from structured(scene graphs) or free-form(sentences) descriptions, most of them only guarantee the image-level semantical consistency, i.e. the generated image matching the semantic meaning of the description. They still lack the investigations on synthesizing the images in a more controllable way, like finely manipulating the visual appearance of every object. Therefore, to generate the images with preferred objects and rich interactions, we propose a semi-parametric method, PasteGAN, for generating the image from the scene graph and the image crops, where spatial arrangements of the objects and their pair-wise relationships are defined by the scene graph and the object appearances are determined by the given object crops. To enhance the interactions of the objects in the output, we design a Crop Refining Network and an Object-Image Fuser to embed the objects as well as their relationships into one map. Multiple losses work collaboratively to guarantee the generated images highly respecting the crops and complying with the scene graphs while maintaining excellent image quality. A crop selector is also proposed to pick the most-compatible crops from our external object tank by encoding the interactions around the objects in the scene graph if the crops are not provided. Evaluated on Visual Genome and COCO-Stuff dataset, our proposed method significantly outperforms the SOTA methods on Inception Score, Diversity Score and Fr'echet Inception Distance. Extensive experiments also demonstrate our method’s ability to generate complex and diverse images with given objects.
Tasks	Image Generation
Published	2019-05-05
URL	https://arxiv.org/abs/1905.01608v2
PDF	https://arxiv.org/pdf/1905.01608v2.pdf
PWC	https://paperswithcode.com/paper/pastegan-a-semi-parametric-method-to-generate
Repo
Framework

Adversarial Representation Active Learning


Title	Adversarial Representation Active Learning
Authors	Ali Mottaghi, Serena Yeung
Abstract	Active learning aims to develop label-efficient algorithms by querying the most informative samples to be labeled by an oracle. The design of efficient training methods that require fewer labels is an important research direction that allows more effective use of computational and human resources for labeling and training deep neural networks. In this work, we demonstrate how we can use recent advances in deep generative models, to outperform the state-of-the-art in achieving the highest classification accuracy using as few labels as possible. Unlike previous approaches, our approach uses not only labeled images to train the classifier but also unlabeled images and generated images for co-training the whole model. Our experiments show that the proposed method significantly outperforms existing approaches in active learning on a wide range of datasets (MNIST, CIFAR-10, SVHN, CelebA, and ImageNet).
Tasks	Active Learning
Published	2019-12-20
URL	https://arxiv.org/abs/1912.09720v1
PDF	https://arxiv.org/pdf/1912.09720v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-representation-active-learning
Repo
Framework

Constructing Hierarchical Q&A Datasets for Video Story Understanding


Title	Constructing Hierarchical Q&A Datasets for Video Story Understanding
Authors	Yu-Jung Heo, Kyoung-Woon On, Seongho Choi, Jaeseo Lim, Jinah Kim, Jeh-Kwang Ryu, Byung-Chull Bae, Byoung-Tak Zhang
Abstract	Video understanding is emerging as a new paradigm for studying human-like AI. Question-and-Answering (Q&A) is used as a general benchmark to measure the level of intelligence for video understanding. While several previous studies have suggested datasets for video Q&A tasks, they did not really incorporate story-level understanding, resulting in highly-biased and lack of variance in degree of question difficulty. In this paper, we propose a hierarchical method for building Q&A datasets, i.e. hierarchical difficulty levels. We introduce three criteria for video story understanding, i.e. memory capacity, logical complexity, and DIKW (Data-Information-Knowledge-Wisdom) pyramid. We discuss how three-dimensional map constructed from these criteria can be used as a metric for evaluating the levels of intelligence relating to video story understanding.
Tasks	Video Understanding
Published	2019-04-01
URL	http://arxiv.org/abs/1904.00623v1
PDF	http://arxiv.org/pdf/1904.00623v1.pdf
PWC	https://paperswithcode.com/paper/constructing-hierarchical-qa-datasets-for
Repo
Framework

Learning to Collocate Neural Modules for Image Captioning


Title	Learning to Collocate Neural Modules for Image Captioning
Authors	Xu Yang, Hanwang Zhang, Jianfei Cai
Abstract	We do not speak word by word from scratch; our brain quickly structures a pattern like \textsc{sth do sth at someplace} and then fill in the detailed descriptions. To render existing encoder-decoder image captioners such human-like reasoning, we propose a novel framework: learning to Collocate Neural Modules (CNM), to generate the `inner pattern’ connecting visual encoder and language decoder. Unlike the widely-used neural module networks in visual Q&A, where the language (ie, question) is fully observable, CNM for captioning is more challenging as the language is being generated and thus is partially observable. To this end, we make the following technical contributions for CNM training: 1) compact module design — one for function words and three for visual content words (eg, noun, adjective, and verb), 2) soft module fusion and multi-step module execution, robustifying the visual reasoning in partial observation, 3) a linguistic loss for module controller being faithful to part-of-speech collocations (eg, adjective is before noun). Extensive experiments on the challenging MS-COCO image captioning benchmark validate the effectiveness of our CNM image captioner. In particular, CNM achieves a new state-of-the-art 127.9 CIDEr-D on Karpathy split and a single-model 126.0 c40 on the official server. CNM is also robust to few training samples, eg, by training only one sentence per image, CNM can halve the performance loss compared to a strong baseline. \|
Tasks	Image Captioning, Visual Question Answering, Visual Reasoning
Published	2019-04-18
URL	http://arxiv.org/abs/1904.08608v1
PDF	http://arxiv.org/pdf/1904.08608v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-collocate-neural-modules-for
Repo
Framework

A Multistep Lyapunov Approach for Finite-Time Analysis of Biased Stochastic Approximation


Title	A Multistep Lyapunov Approach for Finite-Time Analysis of Biased Stochastic Approximation
Authors	Gang Wang, Bingcong Li, Georgios B. Giannakis
Abstract	Motivated by the widespread use of temporal-difference (TD-) and Q-learning algorithms in reinforcement learning, this paper studies a class of biased stochastic approximation (SA) procedures under a mild “ergodic-like” assumption on the underlying stochastic noise sequence. Building upon a carefully designed multistep Lyapunov function that looks ahead to several future updates to accommodate the stochastic perturbations (for control of the gradient bias), we prove a general result on the convergence of the iterates, and use it to derive non-asymptotic bounds on the mean-square error in the case of constant stepsizes. This novel looking-ahead viewpoint renders finite-time analysis of biased SA algorithms under a large family of stochastic perturbations possible. For direct comparison with existing contributions, we also demonstrate these bounds by applying them to TD- and Q-learning with linear function approximation, under the practical Markov chain observation model. The resultant finite-time error bound for both the TD- as well as the Q-learning algorithms is the first of its kind, in the sense that it holds i) for the unmodified versions (i.e., without making any modifications to the parameter updates) using even nonlinear function approximators; as well as for Markov chains ii) under general mixing conditions and iii) starting from any initial distribution, at least one of which has to be violated for existing results to be applicable.
Tasks	Q-Learning
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04299v2
PDF	https://arxiv.org/pdf/1909.04299v2.pdf
PWC	https://paperswithcode.com/paper/a-multistep-lyapunov-approach-for-finite-time
Repo
Framework

Hierarchical Planning in the IPC


Title	Hierarchical Planning in the IPC
Authors	D. Höller, G. Behnke, P. Bercher, S. Biundo, H. Fiorino, D. Pellier, R. Alford
Abstract	Over the last year, the amount of research in hierarchical planning has increased, leading to significant improvements in the performance of planners. However, the research is diverging and planners are somewhat hard to compare against each other. This is mostly caused by the fact that there is no standard set of benchmark domains, nor even a common description language for hierarchical planning problems. As a consequence, the available planners support a widely varying set of features and (almost) none of them can solve (or even parse) any problem developed for another planner. With this paper, we propose to create a new track for the IPC in which hierarchical planners will compete. This competition will result in a standardised description language, broader support for core features of that language among planners, a set of benchmark problems, a means to fairly and objectively compare HTN planners, and for new challenges for planners.
Tasks
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04405v1
PDF	https://arxiv.org/pdf/1909.04405v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-planning-in-the-ipc
Repo
Framework

Show, Price and Negotiate: A Hierarchical Attention Recurrent Visual Negotiator


Title	Show, Price and Negotiate: A Hierarchical Attention Recurrent Visual Negotiator
Authors	Amin Parvaneh, Ehsan Abbasnejad, Qi Wu, Javen Shi
Abstract	Negotiation, as a seller or buyer, is an essential and complicated aspect of online shopping. It is challenging for an intelligent agent because it requires (1) extracting and utilising information from multiple sources (e.g. photos, texts, and numerals), (2) predicting a suitable price for the products to reach the best possible agreement, (3) expressing the intention conditioned on the price in a natural language and (4) consistent pricing. Conventional dialog systems do not address these problems well. For example, we believe that the price should be the driving factor for the negotiation and understood by the agent. But conventionally, the price was simply treated as a word token i.e. being part of a sentence and sharing the same word embedding space with other words. To that end, we propose our Visual Negotiator that comprises of an end-to-end deep learning model that anticipates an initial agreement price and updates it while generating compelling supporting dialog. For (1), our visual negotiator utilises attention mechanism to extract relevant information from the images and textual description, and feeds the price (and later refined price) as separate important input to several stages of the system, instead of simply being part of a sentence; For (2), we use the attention to learn a price embedding to estimate an initial value; Subsequently, for (3) we generate the supporting dialog in an encoder-decoder fashion that utilises the price embedding. Further, we use a hierarchical recurrent model that learns to refine the price at one level while generating the supporting dialog in another; For (4), this hierarchical model provides consistent pricing. Empirically, we show that our model significantly improves negotiation on the CraigslistBargain dataset, in terms of the agreement price, price consistency, and the language quality.
Tasks
Published	2019-05-07
URL	https://arxiv.org/abs/1905.03721v1
PDF	https://arxiv.org/pdf/1905.03721v1.pdf
PWC	https://paperswithcode.com/paper/190503721
Repo
Framework

A framework for seizure detection using effective connectivity, graph theory and deep modular neural networks


Title	A framework for seizure detection using effective connectivity, graph theory and deep modular neural networks
Authors	Behnaz Akbarian, Abbas Erfanian
Abstract	Objective The electrical characteristics of the EEG signals can be used for seizure detection. Statistical independence between different brain regions is measured by functional brain connectivity (FBC). Specific directional effects can’t consider by FBC and thus effective brain connectivity (EBC) is used to measure causal intervention between one neuronal region and the rest of the neuronal regions. Our main purpose is to provide a reliable automatic seizure detection approach. Methods In this study, three new methods are provided. Deep modular neural network (DMNN) is developed based on a combination of various EBC classification results in the different frequencies. Another method is named “modular effective neural networks (MENN)". This method combines the classification results of the three different EBC in the specific frequency. “Modular frequency neural networks (MFNN)” is another method that combines the classification results of the specific EBC in the seven different frequencies. Results The mean accuracy of the MFNN are 97.14%, 98.53%, and 97.91% using directed transfer function, directed coherence, and generalized partial directed coherence, respectively. Using the MENN, the highest mean accuracy is 98.34%. Finally, DMNN has the highest mean accuracy which is equal to 99.43. To our best knowledge, the proposed method is a new method that provides the high accuracy in comparison to other studies which used MIT-CHB database. Conclusion and significance The knowledge of structure-function relationships between different areas of the brain is necessary for characterizing the underlying dynamics. Hence, features based on EBC can provide a reliable automatic seizure detection approach.
Tasks	EEG, Seizure Detection
Published	2019-09-06
URL	https://arxiv.org/abs/1909.03091v1
PDF	https://arxiv.org/pdf/1909.03091v1.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-seizure-detection-using
Repo
Framework

Robust Visual Tracking Revisited: From Correlation Filter to Template Matching


Title	Robust Visual Tracking Revisited: From Correlation Filter to Template Matching
Authors	Fanghui Liu, Chen Gong, Xiaolin Huang, Tao Zhou, Jie Yang, Dacheng Tao
Abstract	In this paper, we propose a novel matching based tracker by investigating the relationship between template matching and the recent popular correlation filter based trackers (CFTs). Compared to the correlation operation in CFTs, a sophisticated similarity metric termed “mutual buddies similarity” (MBS) is proposed to exploit the relationship of multiple reciprocal nearest neighbors for target matching. By doing so, our tracker obtains powerful discriminative ability on distinguishing target and background as demonstrated by both empirical and theoretical analyses. Besides, instead of utilizing single template with the improper updating scheme in CFTs, we design a novel online template updating strategy named “memory filtering” (MF), which aims to select a certain amount of representative and reliable tracking results in history to construct the current stable and expressive template set. This scheme is beneficial for the proposed tracker to comprehensively “understand” the target appearance variations, “recall” some stable results. Both qualitative and quantitative evaluations on two benchmarks suggest that the proposed tracking method performs favorably against some recently developed CFTs and other competitive trackers.
Tasks	Visual Tracking
Published	2019-04-15
URL	http://arxiv.org/abs/1904.06842v1
PDF	http://arxiv.org/pdf/1904.06842v1.pdf
PWC	https://paperswithcode.com/paper/robust-visual-tracking-revisited-from
Repo
Framework