May 5, 2019

2795 words 14 mins read

Paper Group ANR 536

Relevant based structure learning for feature selection. Explaining Radiological Emphysema Subtypes with Unsupervised Texture Prototypes: MESA COPD Study. Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds. Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images. Adversarial Top-$K$ Ranking. Compression of …

Relevant based structure learning for feature selection


Title	Relevant based structure learning for feature selection
Authors	Hadi Zare, Mojtaba Niazi
Abstract	Feature selection is an important task in many problems occurring in pattern recognition, bioinformatics, machine learning and data mining applications. The feature selection approach enables us to reduce the computation burden and the falling accuracy effect of dealing with huge number of features in typical learning problems. There is a variety of techniques for feature selection in supervised learning problems based on different selection metrics. In this paper, we propose a novel unified framework for feature selection built on the graphical models and information theoretic tools. The proposed approach exploits the structure learning among features to select more relevant and less redundant features to the predictive modeling problem according to a primary novel likelihood based criterion. In line with the selection of the optimal subset of features through the proposed method, it provides us the Bayesian network classifier without the additional cost of model training on the selected subset of features. The optimal properties of our method are established through empirical studies and computational complexity analysis. Furthermore the proposed approach is evaluated on a bunch of benchmark datasets based on the well-known classification algorithms. Extensive experiments confirm the significant improvement of the proposed approach compared to the earlier works.
Tasks	Feature Selection
Published	2016-08-29
URL	http://arxiv.org/abs/1608.07934v1
PDF	http://arxiv.org/pdf/1608.07934v1.pdf
PWC	https://paperswithcode.com/paper/relevant-based-structure-learning-for-feature
Repo
Framework

Explaining Radiological Emphysema Subtypes with Unsupervised Texture Prototypes: MESA COPD Study


Title	Explaining Radiological Emphysema Subtypes with Unsupervised Texture Prototypes: MESA COPD Study
Authors	Jie Yang, Elsa D. Angelini, Benjamin M. Smith, John H. M. Austin, Eric A. Hoffman, David A. Bluemke, R. Graham Barr, Andrew F. Laine
Abstract	Pulmonary emphysema is traditionally subcategorized into three subtypes, which have distinct radiological appearances on computed tomography (CT) and can help with the diagnosis of chronic obstructive pulmonary disease (COPD). Automated texture-based quantification of emphysema subtypes has been successfully implemented via supervised learning of these three emphysema subtypes. In this work, we demonstrate that unsupervised learning on a large heterogeneous database of CT scans can generate texture prototypes that are visually homogeneous and distinct, reproducible across subjects, and capable of predicting accurately the three standard radiological subtypes. These texture prototypes enable automated labeling of lung volumes, and open the way to new interpretations of lung CT scans with finer subtyping of emphysema.
Tasks	Computed Tomography (CT)
Published	2016-12-05
URL	http://arxiv.org/abs/1612.01820v1
PDF	http://arxiv.org/pdf/1612.01820v1.pdf
PWC	https://paperswithcode.com/paper/explaining-radiological-emphysema-subtypes
Repo
Framework

Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds


Title	Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds
Authors	Hongyi Zhang, Sashank J. Reddi, Suvrit Sra
Abstract	We study optimization of finite sums of geodesically smooth functions on Riemannian manifolds. Although variance reduction techniques for optimizing finite-sums have witnessed tremendous attention in the recent years, existing work is limited to vector space problems. We introduce Riemannian SVRG (RSVRG), a new variance reduced Riemannian optimization method. We analyze RSVRG for both geodesically convex and nonconvex (smooth) functions. Our analysis reveals that RSVRG inherits advantages of the usual SVRG method, but with factors depending on curvature of the manifold that influence its convergence. To our knowledge, RSVRG is the first provably fast stochastic Riemannian method. Moreover, our paper presents the first non-asymptotic complexity analysis (novel even for the batch setting) for nonconvex Riemannian optimization. Our results have several implications; for instance, they offer a Riemannian perspective on variance reduced PCA, which promises a short, transparent convergence analysis.
Tasks	Stochastic Optimization
Published	2016-05-23
URL	http://arxiv.org/abs/1605.07147v2
PDF	http://arxiv.org/pdf/1605.07147v2.pdf
PWC	https://paperswithcode.com/paper/riemannian-svrg-fast-stochastic-optimization
Repo
Framework

Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images


Title	Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images
Authors	Aron Yu, Kristen Grauman
Abstract	Distinguishing subtle differences in attributes is valuable, yet learning to make visual comparisons remains non-trivial. Not only is the number of possible comparisons quadratic in the number of training images, but also access to images adequately spanning the space of fine-grained visual differences is limited. We propose to overcome the sparsity of supervision problem via synthetically generated images. Building on a state-of-the-art image generation engine, we sample pairs of training images exhibiting slight modifications of individual attributes. Augmenting real training image pairs with these examples, we then train attribute ranking models to predict the relative strength of an attribute in novel pairs of real images. Our results on datasets of faces and fashion images show the great promise of bootstrapping imperfect image generators to counteract sample sparsity for learning to rank.
Tasks	Image Generation, Learning-To-Rank
Published	2016-12-19
URL	http://arxiv.org/abs/1612.06341v2
PDF	http://arxiv.org/pdf/1612.06341v2.pdf
PWC	https://paperswithcode.com/paper/semantic-jitter-dense-supervision-for-visual
Repo
Framework

Adversarial Top-$K$ Ranking


Title	Adversarial Top-$K$ Ranking
Authors	Changho Suh, Vincent Y. F. Tan, Renbo Zhao
Abstract	We study the top-$K$ ranking problem where the goal is to recover the set of top-$K$ ranked items out of a large collection of items based on partially revealed preferences. We consider an adversarial crowdsourced setting where there are two population sets, and pairwise comparison samples drawn from one of the populations follow the standard Bradley-Terry-Luce model (i.e., the chance of item $i$ beating item $j$ is proportional to the relative score of item $i$ to item $j$), while in the other population, the corresponding chance is inversely proportional to the relative score. When the relative size of the two populations is known, we characterize the minimax limit on the sample size required (up to a constant) for reliably identifying the top-$K$ items, and demonstrate how it scales with the relative size. Moreover, by leveraging a tensor decomposition method for disambiguating mixture distributions, we extend our result to the more realistic scenario in which the relative population size is unknown, thus establishing an upper bound on the fundamental limit of the sample size for recovering the top-$K$ set.
Tasks
Published	2016-02-15
URL	http://arxiv.org/abs/1602.04567v1
PDF	http://arxiv.org/pdf/1602.04567v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-top-k-ranking
Repo
Framework

Compression of Neural Machine Translation Models via Pruning


Title	Compression of Neural Machine Translation Models via Pruning
Authors	Abigail See, Minh-Thang Luong, Christopher D. Manning
Abstract	Neural Machine Translation (NMT), like many other deep learning domains, typically suffers from over-parameterization, resulting in large storage sizes. This paper examines three simple magnitude-based pruning schemes to compress NMT models, namely class-blind, class-uniform, and class-distribution, which differ in terms of how pruning thresholds are computed for the different classes of weights in the NMT architecture. We demonstrate the efficacy of weight pruning as a compression technique for a state-of-the-art NMT system. We show that an NMT model with over 200 million parameters can be pruned by 40% with very little performance loss as measured on the WMT’14 English-German translation task. This sheds light on the distribution of redundancy in the NMT architecture. Our main result is that with retraining, we can recover and even surpass the original performance with an 80%-pruned model.
Tasks	Machine Translation
Published	2016-06-29
URL	http://arxiv.org/abs/1606.09274v1
PDF	http://arxiv.org/pdf/1606.09274v1.pdf
PWC	https://paperswithcode.com/paper/compression-of-neural-machine-translation
Repo
Framework

Sparse Coding and Counting for Robust Visual Tracking


Title	Sparse Coding and Counting for Robust Visual Tracking
Authors	Risheng Liu, Jing Wang, Yiyang Wang, Zhixun Su, Yu Cai
Abstract	In this paper, we propose a novel sparse coding and counting method under Bayesian framwork for visual tracking. In contrast to existing methods, the proposed method employs the combination of L0 and L1 norm to regularize the linear coefficients of incrementally updated linear basis. The sparsity constraint enables the tracker to effectively handle difficult challenges, such as occlusion or image corruption. To achieve realtime processing, we propose a fast and efficient numerical algorithm for solving the proposed model. Although it is an NP-hard problem, the proposed accelerated proximal gradient (APG) approach is guaranteed to converge to a solution quickly. Besides, we provide a closed solution of combining L0 and L1 regularized representation to obtain better sparsity. Experimental results on challenging video sequences demonstrate that the proposed method achieves state-of-the-art results both in accuracy and speed.
Tasks	Visual Tracking
Published	2016-05-28
URL	http://arxiv.org/abs/1605.08881v1
PDF	http://arxiv.org/pdf/1605.08881v1.pdf
PWC	https://paperswithcode.com/paper/sparse-coding-and-counting-for-robust-visual
Repo
Framework

An Online Universal Classifier for Binary, Multi-class and Multi-label Classification


Title	An Online Universal Classifier for Binary, Multi-class and Multi-label Classification
Authors	Meng Joo Er, Rajasekar Venkatesan, Ning Wang
Abstract	Classification involves the learning of the mapping function that associates input samples to corresponding target label. There are two major categories of classification problems: Single-label classification and Multi-label classification. Traditional binary and multi-class classifications are sub-categories of single-label classification. Several classifiers are developed for binary, multi-class and multi-label classification problems, but there are no classifiers available in the literature capable of performing all three types of classification. In this paper, a novel online universal classifier capable of performing all the three types of classification is proposed. Being a high speed online classifier, the proposed technique can be applied to streaming data applications. The performance of the developed classifier is evaluated using datasets from binary, multi-class and multi-label problems. The results obtained are compared with state-of-the-art techniques from each of the classification types.
Tasks	Multi-Label Classification
Published	2016-09-03
URL	http://arxiv.org/abs/1609.00843v1
PDF	http://arxiv.org/pdf/1609.00843v1.pdf
PWC	https://paperswithcode.com/paper/an-online-universal-classifier-for-binary
Repo
Framework

Streaming View Learning


Title	Streaming View Learning
Authors	Chang Xu, Dacheng Tao, Chao Xu
Abstract	An underlying assumption in conventional multi-view learning algorithms is that all views can be simultaneously accessed. However, due to various factors when collecting and pre-processing data from different views, the streaming view setting, in which views arrive in a streaming manner, is becoming more common. By assuming that the subspaces of a multi-view model trained over past views are stable, here we fine tune their combination weights such that the well-trained multi-view model is compatible with new views. This largely overcomes the burden of learning new view functions and updating past view functions. We theoretically examine convergence issues and the influence of streaming views in the proposed algorithm. Experimental results on real-world datasets suggest that studying the streaming views problem in multi-view learning is significant and that the proposed algorithm can effectively handle streaming views in different applications.
Tasks	MULTI-VIEW LEARNING
Published	2016-04-28
URL	http://arxiv.org/abs/1604.08291v1
PDF	http://arxiv.org/pdf/1604.08291v1.pdf
PWC	https://paperswithcode.com/paper/streaming-view-learning
Repo
Framework

Detecting Unseen Falls from Wearable Devices using Channel-wise Ensemble of Autoencoders


Title	Detecting Unseen Falls from Wearable Devices using Channel-wise Ensemble of Autoencoders
Authors	Shehroz S. Khan, Babak Taati
Abstract	A fall is an abnormal activity that occurs rarely, so it is hard to collect real data for falls. It is, therefore, difficult to use supervised learning methods to automatically detect falls. Another challenge in using machine learning methods to automatically detect falls is the choice of engineered features. In this paper, we propose to use an ensemble of autoencoders to extract features from different channels of wearable sensor data trained only on normal activities. We show that the traditional approach of choosing a threshold as the maximum of the reconstruction error on the training normal data is not the right way to identify unseen falls. We propose two methods for automatic tightening of reconstruction error from only the normal activities for better identification of unseen falls. We present our results on two activity recognition datasets and show the efficacy of our proposed method against traditional autoencoder models and two standard one-class classification methods.
Tasks	Activity Recognition
Published	2016-10-12
URL	http://arxiv.org/abs/1610.03761v3
PDF	http://arxiv.org/pdf/1610.03761v3.pdf
PWC	https://paperswithcode.com/paper/detecting-unseen-falls-from-wearable-devices
Repo
Framework


Title	Strategic disclosure of opinions on a social network
Authors	Umberto Grandi, Emiliano Lorini, Laurent Perrussel
Abstract	We study the strategic aspects of social influence in a society of agents linked by a trust network, introducing a new class of games called games of influence. A game of influence is an infinite repeated game with incomplete information in which, at each stage of interaction, an agent can make her opinions visible (public) or invisible (private) in order to influence other agents’ opinions. The influence process is mediated by a trust network, as we assume that the opinion of a given agent is only affected by the opinions of those agents that she considers trustworthy (i.e., the agents in the trust network that are directly linked to her). Each agent is endowed with a goal, expressed in a suitable temporal language inspired from linear temporal logic (LTL). We show that games of influence provide a simple abstraction to explore the effects of the trust network structure on the agents’ behaviour, by considering solution concepts from game-theory such as Nash equilibrium, weak dominance and winning strategies.
Tasks
Published	2016-02-05
URL	http://arxiv.org/abs/1602.02710v1
PDF	http://arxiv.org/pdf/1602.02710v1.pdf
PWC	https://paperswithcode.com/paper/strategic-disclosure-of-opinions-on-a-social
Repo
Framework

Cell segmentation with random ferns and graph-cuts


Title	Cell segmentation with random ferns and graph-cuts
Authors	Arnaud Browet, Christophe De Vleeschouwer, Laurent Jacques, Navrita Mathiah, Bechara Saykali, Isabelle Migeotte
Abstract	The progress in imaging techniques have allowed the study of various aspect of cellular mechanisms. To isolate individual cells in live imaging data, we introduce an elegant image segmentation framework that effectively extracts cell boundaries, even in the presence of poor edge details. Our approach works in two stages. First, we estimate pixel interior/border/exterior class probabilities using random ferns. Then, we use an energy minimization framework to compute boundaries whose localization is compliant with the pixel class probabilities. We validate our approach on a manually annotated dataset.
Tasks	Cell Segmentation, Semantic Segmentation
Published	2016-02-17
URL	http://arxiv.org/abs/1602.05439v1
PDF	http://arxiv.org/pdf/1602.05439v1.pdf
PWC	https://paperswithcode.com/paper/cell-segmentation-with-random-ferns-and-graph
Repo
Framework

CaR-FOREST: Joint Classification-Regression Decision Forests for Overlapping Audio Event Detection


Title	CaR-FOREST: Joint Classification-Regression Decision Forests for Overlapping Audio Event Detection
Authors	Huy Phan, Lars Hertel, Marco Maass, Philipp Koch, Alfred Mertins
Abstract	This report describes our submissions to Task2 and Task3 of the DCASE 2016 challenge. The systems aim at dealing with the detection of overlapping audio events in continuous streams, where the detectors are based on random decision forests. The proposed forests are jointly trained for classification and regression simultaneously. Initially, the training is classification-oriented to encourage the trees to select discriminative features from overlapping mixtures to separate positive audio segments from the negative ones. The regression phase is then carried out to let the positive audio segments vote for the event onsets and offsets, and therefore model the temporal structure of audio events. One random decision forest is specifically trained for each event category of interest. Experimental results on the development data show that our systems significantly outperform the baseline on the Task2 evaluation while they are inferior to the baseline in the Task3 evaluation.
Tasks
Published	2016-07-08
URL	http://arxiv.org/abs/1607.02306v2
PDF	http://arxiv.org/pdf/1607.02306v2.pdf
PWC	https://paperswithcode.com/paper/car-forest-joint-classification-regression
Repo
Framework

Exploiting Unlabeled Data for Neural Grammatical Error Detection


Title	Exploiting Unlabeled Data for Neural Grammatical Error Detection
Authors	Zhuoran Liu, Yang Liu
Abstract	Identifying and correcting grammatical errors in the text written by non-native writers has received increasing attention in recent years. Although a number of annotated corpora have been established to facilitate data-driven grammatical error detection and correction approaches, they are still limited in terms of quantity and coverage because human annotation is labor-intensive, time-consuming, and expensive. In this work, we propose to utilize unlabeled data to train neural network based grammatical error detection models. The basic idea is to cast error detection as a binary classification problem and derive positive and negative training examples from unlabeled data. We introduce an attention-based neural network to capture long-distance dependencies that influence the word being detected. Experiments show that the proposed approach significantly outperforms SVMs and convolutional networks with fixed-size context window.
Tasks	Grammatical Error Detection
Published	2016-11-28
URL	http://arxiv.org/abs/1611.08987v2
PDF	http://arxiv.org/pdf/1611.08987v2.pdf
PWC	https://paperswithcode.com/paper/exploiting-unlabeled-data-for-neural
Repo
Framework

Supervised Opinion Aspect Extraction by Exploiting Past Extraction Results


Title	Supervised Opinion Aspect Extraction by Exploiting Past Extraction Results
Authors	Lei Shu, Bing Liu, Hu Xu, Annice Kim
Abstract	One of the key tasks of sentiment analysis of product reviews is to extract product aspects or features that users have expressed opinions on. In this work, we focus on using supervised sequence labeling as the base approach to performing the task. Although several extraction methods using sequence labeling methods such as Conditional Random Fields (CRF) and Hidden Markov Models (HMM) have been proposed, we show that this supervised approach can be significantly improved by exploiting the idea of concept sharing across multiple domains. For example, “screen” is an aspect in iPhone, but not only iPhone has a screen, many electronic devices have screens too. When “screen” appears in a review of a new domain (or product), it is likely to be an aspect too. Knowing this information enables us to do much better extraction in the new domain. This paper proposes a novel extraction method exploiting this idea in the context of supervised sequence labeling. Experimental results show that it produces markedly better results than without using the past information.
Tasks	Aspect Extraction, Sentiment Analysis
Published	2016-12-23
URL	http://arxiv.org/abs/1612.07940v1
PDF	http://arxiv.org/pdf/1612.07940v1.pdf
PWC	https://paperswithcode.com/paper/supervised-opinion-aspect-extraction-by
Repo
Framework