July 27, 2019

2869 words 14 mins read

Paper Group ANR 736

Large-Scale Online Semantic Indexing of Biomedical Articles via an Ensemble of Multi-Label Classification Models. iVQA: Inverse Visual Question Answering. Deep Generative Filter for Motion Deblurring. Convergence Analysis of l0-RLS Adaptive Filter. Gravitational Clustering: A Simple, Robust and Adaptive Approach for Distributed Networks. GQ($λ$) Qu …

Large-Scale Online Semantic Indexing of Biomedical Articles via an Ensemble of Multi-Label Classification Models


Title	Large-Scale Online Semantic Indexing of Biomedical Articles via an Ensemble of Multi-Label Classification Models
Authors	Yannis Papanikolaou, Grigorios Tsoumakas, Manos Laliotis, Nikos Markantonatos, Ioannis Vlahavas
Abstract	Background: In this paper we present the approaches and methods employed in order to deal with a large scale multi-label semantic indexing task of biomedical papers. This work was mainly implemented within the context of the BioASQ challenge of 2014. Methods: The main contribution of this work is a multi-label ensemble method that incorporates a McNemar statistical significance test in order to validate the combination of the constituent machine learning algorithms. Some secondary contributions include a study on the temporal aspects of the BioASQ corpus (observations apply also to the BioASQ’s super-set, the PubMed articles collection) and the proper adaptation of the algorithms used to deal with this challenging classification task. Results: The ensemble method we developed is compared to other approaches in experimental scenarios with subsets of the BioASQ corpus giving positive results. During the BioASQ 2014 challenge we obtained the first place during the first batch and the third in the two following batches. Our success in the BioASQ challenge proved that a fully automated machine-learning approach, which does not implement any heuristics and rule-based approaches, can be highly competitive and outperform other approaches in similar challenging contexts.
Tasks	Multi-Label Classification
Published	2017-04-18
URL	http://arxiv.org/abs/1704.05271v1
PDF	http://arxiv.org/pdf/1704.05271v1.pdf
PWC	https://paperswithcode.com/paper/large-scale-online-semantic-indexing-of
Repo
Framework

iVQA: Inverse Visual Question Answering


Title	iVQA: Inverse Visual Question Answering
Authors	Feng Liu, Tao Xiang, Timothy M. Hospedales, Wankou Yang, Changyin Sun
Abstract	We propose the inverse problem of Visual question answering (iVQA), and explore its suitability as a benchmark for visuo-linguistic understanding. The iVQA task is to generate a question that corresponds to a given image and answer pair. Since the answers are less informative than the questions, and the questions have less learnable bias, an iVQA model needs to better understand the image to be successful than a VQA model. We pose question generation as a multi-modal dynamic inference process and propose an iVQA model that can gradually adjust its focus of attention guided by both a partially generated question and the answer. For evaluation, apart from existing linguistic metrics, we propose a new ranking metric. This metric compares the ground truth question’s rank among a list of distractors, which allows the drawbacks of different algorithms and sources of error to be studied. Experimental results show that our model can generate diverse, grammatically correct and content correlated questions that match the given answer.
Tasks	Question Answering, Question Generation, Visual Question Answering
Published	2017-10-10
URL	http://arxiv.org/abs/1710.03370v2
PDF	http://arxiv.org/pdf/1710.03370v2.pdf
PWC	https://paperswithcode.com/paper/ivqa-inverse-visual-question-answering
Repo
Framework

Deep Generative Filter for Motion Deblurring


Title	Deep Generative Filter for Motion Deblurring
Authors	Sainandan Ramakrishnan, Shubham Pachori. Aalok Gangopadhyay, Shanmuganathan Raman
Abstract	Removing blur caused by camera shake in images has always been a challenging problem in computer vision literature due to its ill-posed nature. Motion blur caused due to the relative motion between the camera and the object in 3D space induces a spatially varying blurring effect over the entire image. In this paper, we propose a novel deep filter based on Generative Adversarial Network (GAN) architecture integrated with global skip connection and dense architecture in order to tackle this problem. Our model, while bypassing the process of blur kernel estimation, significantly reduces the test time which is necessary for practical applications. The experiments on the benchmark datasets prove the effectiveness of the proposed method which outperforms the state-of-the-art blind deblurring algorithms both quantitatively and qualitatively.
Tasks	Deblurring
Published	2017-09-11
URL	http://arxiv.org/abs/1709.03481v1
PDF	http://arxiv.org/pdf/1709.03481v1.pdf
PWC	https://paperswithcode.com/paper/deep-generative-filter-for-motion-deblurring
Repo
Framework

Convergence Analysis of l0-RLS Adaptive Filter


Title	Convergence Analysis of l0-RLS Adaptive Filter
Authors	B. K. Das, S. Mukhopadhyay, M. Chakraborty
Abstract	This paper presents first and second order convergence analysis of the sparsity aware l0-RLS adaptive filter. The theorems 1 and 2 state the steady state value of mean and mean square deviation of the adaptive filter weight vector.
Tasks
Published	2017-10-16
URL	http://arxiv.org/abs/1710.09259v1
PDF	http://arxiv.org/pdf/1710.09259v1.pdf
PWC	https://paperswithcode.com/paper/convergence-analysis-of-l0-rls-adaptive
Repo
Framework

Gravitational Clustering: A Simple, Robust and Adaptive Approach for Distributed Networks


Title	Gravitational Clustering: A Simple, Robust and Adaptive Approach for Distributed Networks
Authors	Patricia Binder, Michael Muma, Abdelhak M. Zoubir
Abstract	Distributed signal processing for wireless sensor networks enables that different devices cooperate to solve different signal processing tasks. A crucial first step is to answer the question: who observes what? Recently, several distributed algorithms have been proposed, which frame the signal/object labelling problem in terms of cluster analysis after extracting source-specific features, however, the number of clusters is assumed to be known. We propose a new method called Gravitational Clustering (GC) to adaptively estimate the time-varying number of clusters based on a set of feature vectors. The key idea is to exploit the physical principle of gravitational force between mass units: streaming-in feature vectors are considered as mass units of fixed position in the feature space, around which mobile mass units are injected at each time instant. The cluster enumeration exploits the fact that the highest attraction on the mobile mass units is exerted by regions with a high density of feature vectors, i.e., gravitational clusters. By sharing estimates among neighboring nodes via a diffusion-adaptation scheme, cooperative and distributed cluster enumeration is achieved. Numerical experiments concerning robustness against outliers, convergence and computational complexity are conducted. The application in a distributed cooperative multi-view camera network illustrates the applicability to real-world problems.
Tasks
Published	2017-08-31
URL	http://arxiv.org/abs/1709.02287v1
PDF	http://arxiv.org/pdf/1709.02287v1.pdf
PWC	https://paperswithcode.com/paper/gravitational-clustering-a-simple-robust-and
Repo
Framework

GQ($λ$) Quick Reference and Implementation Guide


Title	GQ($λ$) Quick Reference and Implementation Guide
Authors	Adam White, Richard S. Sutton
Abstract	This document should serve as a quick reference for and guide to the implementation of linear GQ($\lambda$), a gradient-based off-policy temporal-difference learning algorithm. Explanation of the intuition and theory behind the algorithm are provided elsewhere (e.g., Maei & Sutton 2010, Maei 2011). If you questions or concerns about the content in this document or the attached java code please email Adam White (adam.white@ualberta.ca). The code is provided as part of the source files in the arXiv submission.
Tasks
Published	2017-05-10
URL	http://arxiv.org/abs/1705.03967v1
PDF	http://arxiv.org/pdf/1705.03967v1.pdf
PWC	https://paperswithcode.com/paper/gq-quick-reference-and-implementation-guide
Repo
Framework

Bayesian Network Learning via Topological Order


Title	Bayesian Network Learning via Topological Order
Authors	Young Woong Park, Diego Klabjan
Abstract	We propose a mixed integer programming (MIP) model and iterative algorithms based on topological orders to solve optimization problems with acyclic constraints on a directed graph. The proposed MIP model has a significantly lower number of constraints compared to popular MIP models based on cycle elimination constraints and triangular inequalities. The proposed iterative algorithms use gradient descent and iterative reordering approaches, respectively, for searching topological orders. A computational experiment is presented for the Gaussian Bayesian network learning problem, an optimization problem minimizing the sum of squared errors of regression models with L1 penalty over a feature network with application of gene network inference in bioinformatics.
Tasks
Published	2017-01-20
URL	http://arxiv.org/abs/1701.05654v2
PDF	http://arxiv.org/pdf/1701.05654v2.pdf
PWC	https://paperswithcode.com/paper/bayesian-network-learning-via-topological
Repo
Framework

Segmentation of retinal cysts from Optical Coherence Tomography volumes via selective enhancement


Title	Segmentation of retinal cysts from Optical Coherence Tomography volumes via selective enhancement
Authors	Karthik Gopinath, Jayanthi Sivaswamy
Abstract	Automated and accurate segmentation of cystoid structures in Optical Coherence Tomography (OCT) is of interest in the early detection of retinal diseases. It is, however, a challenging task. We propose a novel method for localizing cysts in 3D OCT volumes. The proposed work is biologically inspired and based on selective enhancement of the cysts, by inducing motion to a given OCT slice. A Convolutional Neural Network (CNN) is designed to learn a mapping function that combines the result of multiple such motions to produce a probability map for cyst locations in a given slice. The final segmentation of cysts is obtained via simple clustering of the detected cyst locations. The proposed method is evaluated on two public datasets and one private dataset. The public datasets include the one released for the OPTIMA Cyst segmentation challenge (OCSC) in MICCAI 2015 and the DME dataset. After training on the OCSC train set, the method achieves a mean Dice Coefficient (DC) of 0.71 on the OCSC test set. The robustness of the algorithm was examined by cross-validation on the DME and AEI (private) datasets and a mean DC values obtained were 0.69 and 0.79, respectively. Overall, the proposed system outperforms all benchmarks. These results underscore the strengths of the proposed method in handling variations in both data acquisition protocols and scanners.
Tasks
Published	2017-08-21
URL	http://arxiv.org/abs/1708.06197v2
PDF	http://arxiv.org/pdf/1708.06197v2.pdf
PWC	https://paperswithcode.com/paper/segmentation-of-retinal-cysts-from-optical
Repo
Framework

Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms


Title	Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms
Authors	Jialei Wang, Lin Xiao
Abstract	We consider empirical risk minimization of linear predictors with convex loss functions. Such problems can be reformulated as convex-concave saddle point problems, and thus are well suitable for primal-dual first-order algorithms. However, primal-dual algorithms often require explicit strongly convex regularization in order to obtain fast linear convergence, and the required dual proximal mapping may not admit closed-form or efficient solution. In this paper, we develop both batch and randomized primal-dual algorithms that can exploit strong convexity from data adaptively and are capable of achieving linear convergence even without regularization. We also present dual-free variants of the adaptive primal-dual algorithms that do not require computing the dual proximal mapping, which are especially suitable for logistic regression.
Tasks
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02624v1
PDF	http://arxiv.org/pdf/1703.02624v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-strong-convexity-from-data-with
Repo
Framework

Fair Kernel Learning


Title	Fair Kernel Learning
Authors	Adrián Pérez-Suay, Valero Laparra, Gonzalo Mateo-García, Jordi Muñoz-Marí, Luis Gómez-Chova, Gustau Camps-Valls
Abstract	New social and economic activities massively exploit big data and machine learning algorithms to do inference on people’s lives. Applications include automatic curricula evaluation, wage determination, and risk assessment for credits and loans. Recently, many governments and institutions have raised concerns about the lack of fairness, equity and ethics in machine learning to treat these problems. It has been shown that not including sensitive features that bias fairness, such as gender or race, is not enough to mitigate the discrimination when other related features are included. Instead, including fairness in the objective function has been shown to be more efficient. We present novel fair regression and dimensionality reduction methods built on a previously proposed fair classification framework. Both methods rely on using the Hilbert Schmidt independence criterion as the fairness term. Unlike previous approaches, this allows us to simplify the problem and to use multiple sensitive variables simultaneously. Replacing the linear formulation by kernel functions allows the methods to deal with nonlinear problems. For both linear and nonlinear formulations the solution reduces to solving simple matrix inversions or generalized eigenvalue problems. This simplifies the evaluation of the solutions for different trade-off values between the predictive error and fairness terms. We illustrate the usefulness of the proposed methods in toy examples, and evaluate their performance on real world datasets to predict income using gender and/or race discrimination as sensitive variables, and contraceptive method prediction under demographic and socio-economic sensitive descriptors.
Tasks	Dimensionality Reduction
Published	2017-10-16
URL	http://arxiv.org/abs/1710.05578v1
PDF	http://arxiv.org/pdf/1710.05578v1.pdf
PWC	https://paperswithcode.com/paper/fair-kernel-learning
Repo
Framework

Globally Normalized Reader


Title	Globally Normalized Reader
Authors	Jonathan Raiman, John Miller
Abstract	Rapid progress has been made towards question answering (QA) systems that can extract answers from text. Existing neural approaches make use of expensive bi-directional attention mechanisms or score all possible answer spans, limiting scalability. We propose instead to cast extractive QA as an iterative search problem: select the answer’s sentence, start word, and end word. This representation reduces the space of each search step and allows computation to be conditionally allocated to promising search paths. We show that globally normalizing the decision process and back-propagating through beam search makes this representation viable and learning efficient. We empirically demonstrate the benefits of this approach using our model, Globally Normalized Reader (GNR), which achieves the second highest single model performance on the Stanford Question Answering Dataset (68.4 EM, 76.21 F1 dev) and is 24.7x faster than bi-attention-flow. We also introduce a data-augmentation method to produce semantically valid examples by aligning named entities to a knowledge base and swapping them with new entities of the same type. This method improves the performance of all models considered in this work and is of independent interest for a variety of NLP tasks.
Tasks	Data Augmentation, Question Answering
Published	2017-09-08
URL	http://arxiv.org/abs/1709.02828v1
PDF	http://arxiv.org/pdf/1709.02828v1.pdf
PWC	https://paperswithcode.com/paper/globally-normalized-reader
Repo
Framework

Analysis of Computational Science Papers from ICCS 2001-2016 using Topic Modeling and Graph Theory


Title	Analysis of Computational Science Papers from ICCS 2001-2016 using Topic Modeling and Graph Theory
Authors	Tesfamariam M. Abuhay, Sergey V. Kovalchuk, Klavdiya O. Bochenina, George Kampis, Valeria V. Krzhizhanovskaya, Michael H. Lees
Abstract	This paper presents results of topic modeling and network models of topics using the International Conference on Computational Science corpus, which contains domain-specific (computational science) papers over sixteen years (a total of 5695 papers). We discuss topical structures of International Conference on Computational Science, how these topics evolve over time in response to the topicality of various problems, technologies and methods, and how all these topics relate to one another. This analysis illustrates multidisciplinary research and collaborations among scientific communities, by constructing static and dynamic networks from the topic modeling results and the keywords of authors. The results of this study give insights about the past and future trends of core discussion topics in computational science. We used the Non-negative Matrix Factorization topic modeling algorithm to discover topics and labeled and grouped results hierarchically.
Tasks
Published	2017-04-18
URL	http://arxiv.org/abs/1705.02203v1
PDF	http://arxiv.org/pdf/1705.02203v1.pdf
PWC	https://paperswithcode.com/paper/analysis-of-computational-science-papers-from
Repo
Framework

Consensus-based Sequence Training for Video Captioning


Title	Consensus-based Sequence Training for Video Captioning
Authors	Sang Phan, Gustav Eje Henter, Yusuke Miyao, Shin’ichi Satoh
Abstract	Captioning models are typically trained using the cross-entropy loss. However, their performance is evaluated on other metrics designed to better correlate with human assessments. Recently, it has been shown that reinforcement learning (RL) can directly optimize these metrics in tasks such as captioning. However, this is computationally costly and requires specifying a baseline reward at each step to make training converge. We propose a fast approach to optimize one’s objective of interest through the REINFORCE algorithm. First we show that, by replacing model samples with ground-truth sentences, RL training can be seen as a form of weighted cross-entropy loss, giving a fast, RL-based pre-training algorithm. Second, we propose to use the consensus among ground-truth captions of the same video as the baseline reward. This can be computed very efficiently. We call the complete proposal Consensus-based Sequence Training (CST). Applied to the MSRVTT video captioning benchmark, our proposals train significantly faster than comparable methods and establish a new state-of-the-art on the task, improving the CIDEr score from 47.3 to 54.2.
Tasks	Video Captioning
Published	2017-12-27
URL	http://arxiv.org/abs/1712.09532v1
PDF	http://arxiv.org/pdf/1712.09532v1.pdf
PWC	https://paperswithcode.com/paper/consensus-based-sequence-training-for-video
Repo
Framework

Exploiting Multi-layer Graph Factorization for Multi-attributed Graph Matching


Title	Exploiting Multi-layer Graph Factorization for Multi-attributed Graph Matching
Authors	Han-Mu Park, Kuk-Jin Yoon
Abstract	Multi-attributed graph matching is a problem of finding correspondences between two sets of data while considering their complex properties described in multiple attributes. However, the information of multiple attributes is likely to be oversimplified during a process that makes an integrated attribute, and this degrades the matching accuracy. For that reason, a multi-layer graph structure-based algorithm has been proposed recently. It can effectively avoid the problem by separating attributes into multiple layers. Nonetheless, there are several remaining issues such as a scalability problem caused by the huge matrix to describe the multi-layer structure and a back-projection problem caused by the continuous relaxation of the quadratic assignment problem. In this work, we propose a novel multi-attributed graph matching algorithm based on the multi-layer graph factorization. We reformulate the problem to be solved with several small matrices that are obtained by factorizing the multi-layer structure. Then, we solve the problem using a convex-concave relaxation procedure for the multi-layer structure. The proposed algorithm exhibits better performance than state-of-the-art algorithms based on the single-layer structure.
Tasks	Graph Matching
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07077v1
PDF	http://arxiv.org/pdf/1704.07077v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-multi-layer-graph-factorization
Repo
Framework

An update on statistical boosting in biomedicine


Title	An update on statistical boosting in biomedicine
Authors	Andreas Mayr, Benjamin Hofner, Elisabeth Waldmann, Tobias Hepp, Olaf Gefeller, Matthias Schmid
Abstract	Statistical boosting algorithms have triggered a lot of research during the last decade. They combine a powerful machine-learning approach with classical statistical modelling, offering various practical advantages like automated variable selection and implicit regularization of effect estimates. They are extremely flexible, as the underlying base-learners (regression functions defining the type of effect for the explanatory variables) can be combined with any kind of loss function (target function to be optimized, defining the type of regression setting). In this review article, we highlight the most recent methodological developments on statistical boosting regarding variable selection, functional regression and advanced time-to-event modelling. Additionally, we provide a short overview on relevant applications of statistical boosting in biomedicine.
Tasks
Published	2017-02-27
URL	http://arxiv.org/abs/1702.08185v1
PDF	http://arxiv.org/pdf/1702.08185v1.pdf
PWC	https://paperswithcode.com/paper/an-update-on-statistical-boosting-in
Repo
Framework