May 5, 2019

3079 words 15 mins read

Paper Group ANR 547

Sharing Hash Codes for Multiple Purposes. A Semi-supervised learning approach to enhance health care Community-based Question Answering: A case study in alcoholism. Learning Interpretable Musical Compositional Rules and Traces. Real-Time Image Distortion Correction: Analysis and Evaluation of FPGA-Compatible Algorithms. Neighborhood Sensitive Mappi …


Title	Sharing Hash Codes for Multiple Purposes
Authors	Wikor Pronobis, Danny Panknin, Johannes Kirschnick, Vignesh Srinivasan, Wojciech Samek, Volker Markl, Manohar Kaul, Klaus-Robert Mueller, Shinichi Nakajima
Abstract	Locality sensitive hashing (LSH) is a powerful tool for sublinear-time approximate nearest neighbor search, and a variety of hashing schemes have been proposed for different dissimilarity measures. However, hash codes significantly depend on the dissimilarity, which prohibits users from adjusting the dissimilarity at query time. In this paper, we propose {multiple purpose LSH (mp-LSH) which shares the hash codes for different dissimilarities. mp-LSH supports L2, cosine, and inner product dissimilarities, and their corresponding weighted sums, where the weights can be adjusted at query time. It also allows us to modify the importance of pre-defined groups of features. Thus, mp-LSH enables us, for example, to retrieve similar items to a query with the user preference taken into account, to find a similar material to a query with some properties (stability, utility, etc.) optimized, and to turn on or off a part of multi-modal information (brightness, color, audio, text, etc.) in image/video retrieval. We theoretically and empirically analyze the performance of three variants of mp-LSH, and demonstrate their usefulness on real-world data sets.
Tasks	Video Retrieval
Published	2016-09-11
URL	http://arxiv.org/abs/1609.03219v3
PDF	http://arxiv.org/pdf/1609.03219v3.pdf
PWC	https://paperswithcode.com/paper/sharing-hash-codes-for-multiple-purposes
Repo
Framework

A Semi-supervised learning approach to enhance health care Community-based Question Answering: A case study in alcoholism


Title	A Semi-supervised learning approach to enhance health care Community-based Question Answering: A case study in alcoholism
Authors	Papis Wongchaisuwat, Diego Klabjan, Siddhartha R. Jonnalagadda
Abstract	Community-based Question Answering (CQA) sites play an important role in addressing health information needs. However, a significant number of posted questions remain unanswered. Automatically answering the posted questions can provide a useful source of information for online health communities. In this study, we developed an algorithm to automatically answer health-related questions based on past questions and answers (QA). We also aimed to understand information embedded within online health content that are good features in identifying valid answers. Our proposed algorithm uses information retrieval techniques to identify candidate answers from resolved QA. In order to rank these candidates, we implemented a semi-supervised leaning algorithm that extracts the best answer to a question. We assessed this approach on a curated corpus from Yahoo! Answers and compared against a rule-based string similarity baseline. On our dataset, the semi-supervised learning algorithm has an accuracy of 86.2%. UMLS-based (health-related) features used in the model enhance the algorithm’s performance by proximately 8 %. A reasonably high rate of accuracy is obtained given that the data is considerably noisy. Important features distinguishing a valid answer from an invalid answer include text length, number of stop words contained in a test question, a distance between the test question and other questions in the corpus as well as a number of overlapping health-related terms between questions. Overall, our automated QA system based on historical QA pairs is shown to be effective according to the data set in this case study. It is developed for general use in the health care domain which can also be applied to other CQA sites.
Tasks	Information Retrieval, Question Answering
Published	2016-07-04
URL	http://arxiv.org/abs/1607.00706v1
PDF	http://arxiv.org/pdf/1607.00706v1.pdf
PWC	https://paperswithcode.com/paper/a-semi-supervised-learning-approach-to
Repo
Framework

Learning Interpretable Musical Compositional Rules and Traces


Title	Learning Interpretable Musical Compositional Rules and Traces
Authors	Haizi Yu, Lav R. Varshney, Guy E. Garnett, Ranjitha Kumar
Abstract	Throughout music history, theorists have identified and documented interpretable rules that capture the decisions of composers. This paper asks, “Can a machine behave like a music theorist?” It presents MUS-ROVER, a self-learning system for automatically discovering rules from symbolic music. MUS-ROVER performs feature learning via $n$-gram models to extract compositional rules — statistical patterns over the resulting features. We evaluate MUS-ROVER on Bach’s (SATB) chorales, demonstrating that it can recover known rules, as well as identify new, characteristic patterns for further study. We discuss how the extracted rules can be used in both machine and human composition.
Tasks
Published	2016-06-17
URL	http://arxiv.org/abs/1606.05572v1
PDF	http://arxiv.org/pdf/1606.05572v1.pdf
PWC	https://paperswithcode.com/paper/learning-interpretable-musical-compositional
Repo
Framework

Real-Time Image Distortion Correction: Analysis and Evaluation of FPGA-Compatible Algorithms


Title	Real-Time Image Distortion Correction: Analysis and Evaluation of FPGA-Compatible Algorithms
Authors	Paolo Di Febbo, Stefano Mattoccia, Carlo Dal Mutto
Abstract	Image distortion correction is a critical pre-processing step for a variety of computer vision and image processing algorithms. Standard real-time software implementations are generally not suited for direct hardware porting, so appropriated versions need to be designed in order to obtain implementations deployable on FPGAs. In this paper, hardware-compatible techniques for image distortion correction are introduced and analyzed in details. The considered solutions are compared in terms of output quality by using a geometrical-error-based approach, with particular emphasis on robustness with respect to increasing lens distortion. The required amount of hardware resources is also estimated for each considered approach.
Tasks
Published	2016-10-30
URL	http://arxiv.org/abs/1610.09712v1
PDF	http://arxiv.org/pdf/1610.09712v1.pdf
PWC	https://paperswithcode.com/paper/real-time-image-distortion-correction
Repo
Framework

Neighborhood Sensitive Mapping for Zero-Shot Classification using Independently Learned Semantic Embeddings


Title	Neighborhood Sensitive Mapping for Zero-Shot Classification using Independently Learned Semantic Embeddings
Authors	Gaurav Singh, Fabrizio Silvestri, John Shawe-Taylor
Abstract	In a traditional setting, classifiers are trained to approximate a target function $f:X \rightarrow Y$ where at least a sample for each $y \in Y$ is presented to the training algorithm. In a zero-shot setting we have a subset of the labels $\hat{Y} \subset Y$ for which we do not observe any corresponding training instance. Still, the function $f$ that we train must be able to correctly assign labels also on $\hat{Y}$. In practice, zero-shot problems are very important especially when the label set is large and the cost of editorially label samples for all possible values in the label set might be prohibitively high. Most recent approaches to zero-shot learning are based on finding and exploiting relationships between labels using semantic embeddings. We show in this paper that semantic embeddings, despite being very good at capturing relationships between labels, are not very good at capturing the relationships among labels in a data-dependent manner. For this reason, we propose a novel two-step process for learning a zero-shot classifier. In the first step, we learn what we call a \emph{property embedding space} capturing the “\emph{learnable}” features of the label set. Then, we exploit the learned properties in order to reduce the generalization error for a linear nearest neighbor-based classifier.
Tasks	Zero-Shot Learning
Published	2016-05-26
URL	http://arxiv.org/abs/1605.08242v2
PDF	http://arxiv.org/pdf/1605.08242v2.pdf
PWC	https://paperswithcode.com/paper/neighborhood-sensitive-mapping-for-zero-shot
Repo
Framework

Self-organization of vocabularies under different interaction orders


Title	Self-organization of vocabularies under different interaction orders
Authors	Javier Vera
Abstract	Traditionally, the formation of vocabularies has been studied by agent-based models (specially, the Naming Game) in which random pairs of agents negotiate word-meaning associations at each discrete time step. This paper proposes a first approximation to a novel question: To what extent the negotiation of word-meaning associations is influenced by the order in which the individuals interact? Automata Networks provide the adequate mathematical framework to explore this question. Computer simulations suggest that on two-dimensional lattices the typical features of the formation of word-meaning associations are recovered under random schemes that update small fractions of the population at the same time.
Tasks
Published	2016-03-17
URL	http://arxiv.org/abs/1603.05350v2
PDF	http://arxiv.org/pdf/1603.05350v2.pdf
PWC	https://paperswithcode.com/paper/self-organization-of-vocabularies-under
Repo
Framework

Finite-sample and asymptotic analysis of generalization ability with an application to penalized regression


Title	Finite-sample and asymptotic analysis of generalization ability with an application to penalized regression
Authors	Ning Xu, Jian Hong, Timothy C. G. Fisher
Abstract	In this paper, we study the performance of extremum estimators from the perspective of generalization ability (GA): the ability of a model to predict outcomes in new samples from the same population. By adapting the classical concentration inequalities, we derive upper bounds on the empirical out-of-sample prediction errors as a function of the in-sample errors, in-sample data size, heaviness in the tails of the error distribution, and model complexity. We show that the error bounds may be used for tuning key estimation hyper-parameters, such as the number of folds $K$ in cross-validation. We also show how $K$ affects the bias-variance trade-off for cross-validation. We demonstrate that the $\mathcal{L}_2$-norm difference between penalized and the corresponding un-penalized regression estimates is directly explained by the GA of the estimates and the GA of empirical moment conditions. Lastly, we prove that all penalized regression estimates are $L_2$-consistent for both the $n \geqslant p$ and the $n < p$ cases. Simulations are used to demonstrate key results. Keywords: generalization ability, upper bound of generalization error, penalized regression, cross-validation, bias-variance trade-off, $\mathcal{L}_2$ difference between penalized and unpenalized regression, lasso, high-dimensional data.
Tasks
Published	2016-09-12
URL	http://arxiv.org/abs/1609.03344v2
PDF	http://arxiv.org/pdf/1609.03344v2.pdf
PWC	https://paperswithcode.com/paper/finite-sample-and-asymptotic-analysis-of
Repo
Framework

Implicit Discourse Relation Classification via Multi-Task Neural Networks


Title	Implicit Discourse Relation Classification via Multi-Task Neural Networks
Authors	Yang Liu, Sujian Li, Xiaodong Zhang, Zhifang Sui
Abstract	Without discourse connectives, classifying implicit discourse relations is a challenging task and a bottleneck for building a practical discourse parser. Previous research usually makes use of one kind of discourse framework such as PDTB or RST to improve the classification performance on discourse relations. Actually, under different discourse annotation frameworks, there exist multiple corpora which have internal connections. To exploit the combination of different discourse corpora, we design related discourse classification tasks specific to a corpus, and propose a novel Convolutional Neural Network embedded multi-task learning system to synthesize these tasks by learning both unique and shared representations for each task. The experimental results on the PDTB implicit discourse relation classification task demonstrate that our model achieves significant gains over baseline systems.
Tasks	Implicit Discourse Relation Classification, Multi-Task Learning, Relation Classification
Published	2016-03-09
URL	http://arxiv.org/abs/1603.02776v1
PDF	http://arxiv.org/pdf/1603.02776v1.pdf
PWC	https://paperswithcode.com/paper/implicit-discourse-relation-classification
Repo
Framework

Sampling-based Gradient Regularization for Capturing Long-Term Dependencies in Recurrent Neural Networks


Title	Sampling-based Gradient Regularization for Capturing Long-Term Dependencies in Recurrent Neural Networks
Authors	Artem Chernodub, Dimitri Nowicki
Abstract	Vanishing (and exploding) gradients effect is a common problem for recurrent neural networks with nonlinear activation functions which use backpropagation method for calculation of derivatives. Deep feedforward neural networks with many hidden layers also suffer from this effect. In this paper we propose a novel universal technique that makes the norm of the gradient stay in the suitable range. We construct a way to estimate a contribution of each training example to the norm of the long-term components of the target function s gradient. Using this subroutine we can construct mini-batches for the stochastic gradient descent (SGD) training that leads to high performance and accuracy of the trained network even for very complex tasks. We provide a straightforward mathematical estimation of minibatch s impact on for the gradient norm and prove its correctness theoretically. To check our framework experimentally we use some special synthetic benchmarks for testing RNNs on ability to capture long-term dependencies. Our network can detect links between events in the (temporal) sequence at the range approx. 100 and longer.
Tasks
Published	2016-06-24
URL	http://arxiv.org/abs/1606.07767v3
PDF	http://arxiv.org/pdf/1606.07767v3.pdf
PWC	https://paperswithcode.com/paper/sampling-based-gradient-regularization-for
Repo
Framework

Bioinformatics and Classical Literary Study


Title	Bioinformatics and Classical Literary Study
Authors	Pramit Chaudhuri, Joseph P. Dexter
Abstract	This paper describes the Quantitative Criticism Lab, a collaborative initiative between classicists, quantitative biologists, and computer scientists to apply ideas and methods drawn from the sciences to the study of literature. A core goal of the project is the use of computational biology, natural language processing, and machine learning techniques to investigate authorial style, intertextuality, and related phenomena of literary significance. As a case study in our approach, here we review the use of sequence alignment, a common technique in genomics and computational linguistics, to detect intertextuality in Latin literature. Sequence alignment is distinguished by its ability to find inexact verbal similarities, which makes it ideal for identifying phonetic echoes in large corpora of Latin texts. Although especially suited to Latin, sequence alignment in principle can be extended to many other languages.
Tasks
Published	2016-02-29
URL	http://arxiv.org/abs/1602.08844v2
PDF	http://arxiv.org/pdf/1602.08844v2.pdf
PWC	https://paperswithcode.com/paper/bioinformatics-and-classical-literary-study
Repo
Framework

Diagnosing editorial strategies of Chilean media on Twitter using an automatic news classifier


Title	Diagnosing editorial strategies of Chilean media on Twitter using an automatic news classifier
Authors	Matthieu Vernier, Luis Carcamo, Eliana Scheihing
Abstract	In Chile, does not exist an independent entity that publishes quantitative or qualitative surveys to understand the traditional media environment and its adaptation on the Social Web. Nowadays, Chilean newsreaders are increasingly using social web platforms as their primary source of information, among which Twitter plays a central role. Historical media and pure players are developing different strategies to increase their audience and influence on this platform. In this article, we propose a methodology based on data mining techniques to provide a first level of analysis of the new Chilean media environment. We use a crawling technique to mine news streams of 37 different Chilean media actively presents on Twitter and propose several indicators to compare them. We analyze their volumes of production, their potential audience, and using NLP techniques, we explore the content of their production: their editorial line and their geographic coverage.
Tasks
Published	2016-05-24
URL	http://arxiv.org/abs/1605.07260v1
PDF	http://arxiv.org/pdf/1605.07260v1.pdf
PWC	https://paperswithcode.com/paper/diagnosing-editorial-strategies-of-chilean
Repo
Framework

Maximizing Non-Monotone DR-Submodular Functions with Cardinality Constraints


Title	Maximizing Non-Monotone DR-Submodular Functions with Cardinality Constraints
Authors	Ali Khodabakhsh, Evdokia Nikolova
Abstract	We consider the problem of maximizing a non-monotone DR-submodular function subject to a cardinality constraint. Diminishing returns (DR) submodularity is a generalization of the diminishing returns property for functions defined over the integer lattice. This generalization can be used to solve many machine learning or combinatorial optimization problems such as optimal budget allocation, revenue maximization, etc. In this work we propose the first polynomial-time approximation algorithms for non-monotone constrained maximization. We implement our algorithms for a revenue maximization problem with a real-world dataset to check their efficiency and performance.
Tasks	Combinatorial Optimization
Published	2016-11-29
URL	http://arxiv.org/abs/1611.09474v2
PDF	http://arxiv.org/pdf/1611.09474v2.pdf
PWC	https://paperswithcode.com/paper/maximizing-non-monotone-dr-submodular
Repo
Framework

Face Recognition Using Deep Multi-Pose Representations


Title	Face Recognition Using Deep Multi-Pose Representations
Authors	Wael AbdAlmageed, Yue Wua, Stephen Rawlsa, Shai Harel, Tal Hassner, Iacopo Masi, Jongmoo Choi, Jatuporn Toy Leksut, Jungyeon Kim, Prem Natarajan, Ram Nevatia, Gerard Medioni
Abstract	We introduce our method and system for face recognition using multiple pose-aware deep learning models. In our representation, a face image is processed by several pose-specific deep convolutional neural network (CNN) models to generate multiple pose-specific features. 3D rendering is used to generate multiple face poses from the input image. Sensitivity of the recognition system to pose variations is reduced since we use an ensemble of pose-specific CNN features. The paper presents extensive experimental results on the effect of landmark detection, CNN layer selection and pose model selection on the performance of the recognition pipeline. Our novel representation achieves better results than the state-of-the-art on IARPA’s CS2 and NIST’s IJB-A in both verification and identification (i.e. search) tasks.
Tasks	Face Recognition, Face Verification, Model Selection
Published	2016-03-23
URL	http://arxiv.org/abs/1603.07388v1
PDF	http://arxiv.org/pdf/1603.07388v1.pdf
PWC	https://paperswithcode.com/paper/face-recognition-using-deep-multi-pose
Repo
Framework

Rate-Distortion Bounds on Bayes Risk in Supervised Learning


Title	Rate-Distortion Bounds on Bayes Risk in Supervised Learning
Authors	Matthew Nokleby, Ahmad Beirami, Robert Calderbank
Abstract	We present an information-theoretic framework for bounding the number of labeled samples needed to train a classifier in a parametric Bayesian setting. We derive bounds on the average $L_p$ distance between the learned classifier and the true maximum a posteriori classifier, which are well-established surrogates for the excess classification error due to imperfect learning. We provide lower and upper bounds on the rate-distortion function, using $L_p$ loss as the distortion measure, of a maximum a priori classifier in terms of the differential entropy of the posterior distribution and a quantity called the interpolation dimension, which characterizes the complexity of the parametric distribution family. In addition to expressing the information content of a classifier in terms of lossy compression, the rate-distortion function also expresses the minimum number of bits a learning machine needs to extract from training data to learn a classifier to within a specified $L_p$ tolerance. We use results from universal source coding to express the information content in the training data in terms of the Fisher information of the parametric family and the number of training samples available. The result is a framework for computing lower bounds on the Bayes $L_p$ risk. This framework complements the well-known probably approximately correct (PAC) framework, which provides minimax risk bounds involving the Vapnik-Chervonenkis dimension or Rademacher complexity. Whereas the PAC framework provides upper bounds the risk for the worst-case data distribution, the proposed rate-distortion framework lower bounds the risk averaged over the data distribution. We evaluate the bounds for a variety of data models, including categorical, multinomial, and Gaussian models. In each case the bounds are provably tight orderwise, and in two cases we prove that the bounds are tight up to multiplicative constants.
Tasks
Published	2016-05-08
URL	http://arxiv.org/abs/1605.02268v2
PDF	http://arxiv.org/pdf/1605.02268v2.pdf
PWC	https://paperswithcode.com/paper/rate-distortion-bounds-on-bayes-risk-in
Repo
Framework

Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples


Title	Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
Authors	Nicolas Papernot, Patrick McDaniel, Ian Goodfellow
Abstract	Many machine learning models are vulnerable to adversarial examples: inputs that are specially crafted to cause a machine learning model to produce an incorrect output. Adversarial examples that affect one model often affect another model, even if the two models have different architectures or were trained on different training sets, so long as both models were trained to perform the same task. An attacker may therefore train their own substitute model, craft adversarial examples against the substitute, and transfer them to a victim model, with very little information about the victim. Recent work has further developed a technique that uses the victim model as an oracle to label a synthetic training set for the substitute, so the attacker need not even collect a training set to mount the attack. We extend these recent techniques using reservoir sampling to greatly enhance the efficiency of the training procedure for the substitute model. We introduce new transferability attacks between previously unexplored (substitute, victim) pairs of machine learning model classes, most notably SVMs and decision trees. We demonstrate our attacks on two commercial machine learning classification systems from Amazon (96.19% misclassification rate) and Google (88.94%) using only 800 queries of the victim model, thereby showing that existing machine learning approaches are in general vulnerable to systematic black-box attacks regardless of their structure.
Tasks
Published	2016-05-24
URL	http://arxiv.org/abs/1605.07277v1
PDF	http://arxiv.org/pdf/1605.07277v1.pdf
PWC	https://paperswithcode.com/paper/transferability-in-machine-learning-from
Repo
Framework