May 6, 2019

3054 words 15 mins read

Paper Group ANR 330

Exponential Family Embeddings. Gaussian Copula Variational Autoencoders for Mixed Data. Fast Multi-Layer Laplacian Enhancement. Statistical Learning for OCR Text Correction. Improved Achievability and Converse Bounds for Erdős-Rényi Graph Matching. An integrated Graphical User Interface for Debugging Answer Set Programs. A centralized reinforcement …

Exponential Family Embeddings


Title	Exponential Family Embeddings
Authors	Maja R. Rudolph, Francisco J. R. Ruiz, Stephan Mandt, David M. Blei
Abstract	Word embeddings are a powerful approach for capturing semantic similarity among terms in a vocabulary. In this paper, we develop exponential family embeddings, a class of methods that extends the idea of word embeddings to other types of high-dimensional data. As examples, we studied neural data with real-valued observations, count data from a market basket analysis, and ratings data from a movie recommendation system. The main idea is to model each observation conditioned on a set of other observations. This set is called the context, and the way the context is defined is a modeling choice that depends on the problem. In language the context is the surrounding words; in neuroscience the context is close-by neurons; in market basket data the context is other items in the shopping cart. Each type of embedding model defines the context, the exponential family of conditional distributions, and how the latent embedding vectors are shared across data. We infer the embeddings with a scalable algorithm based on stochastic gradient descent. On all three applications - neural activity of zebrafish, users’ shopping behavior, and movie ratings - we found exponential family embedding models to be more effective than other types of dimension reduction. They better reconstruct held-out data and find interesting qualitative structure.
Tasks	Dimensionality Reduction, Semantic Similarity, Semantic Textual Similarity, Word Embeddings
Published	2016-08-02
URL	http://arxiv.org/abs/1608.00778v2
PDF	http://arxiv.org/pdf/1608.00778v2.pdf
PWC	https://paperswithcode.com/paper/exponential-family-embeddings
Repo
Framework

Gaussian Copula Variational Autoencoders for Mixed Data


Title	Gaussian Copula Variational Autoencoders for Mixed Data
Authors	Suwon Suh, Seungjin Choi
Abstract	The variational autoencoder (VAE) is a generative model with continuous latent variables where a pair of probabilistic encoder (bottom-up) and decoder (top-down) is jointly learned by stochastic gradient variational Bayes. We first elaborate Gaussian VAE, approximating the local covariance matrix of the decoder as an outer product of the principal direction at a position determined by a sample drawn from Gaussian distribution. We show that this model, referred to as VAE-ROC, better captures the data manifold, compared to the standard Gaussian VAE where independent multivariate Gaussian was used to model the decoder. Then we extend the VAE-ROC to handle mixed categorical and continuous data. To this end, we employ Gaussian copula to model the local dependency in mixed categorical and continuous data, leading to {\em Gaussian copula variational autoencoder} (GCVAE). As in VAE-ROC, we use the rank-one approximation for the covariance in the Gaussian copula, to capture the local dependency structure in the mixed data. Experiments on various datasets demonstrate the useful behaviour of VAE-ROC and GCVAE, compared to the standard VAE.
Tasks
Published	2016-04-18
URL	http://arxiv.org/abs/1604.04960v1
PDF	http://arxiv.org/pdf/1604.04960v1.pdf
PWC	https://paperswithcode.com/paper/gaussian-copula-variational-autoencoders-for
Repo
Framework

Fast Multi-Layer Laplacian Enhancement


Title	Fast Multi-Layer Laplacian Enhancement
Authors	Hossein Talebi, Peyman Milanfar
Abstract	A novel, fast and practical way of enhancing images is introduced in this paper. Our approach builds on Laplacian operators of well-known edge-aware kernels, such as bilateral and nonlocal means, and extends these filter’s capabilities to perform more effective and fast image smoothing, sharpening and tone manipulation. We propose an approximation of the Laplacian, which does not require normalization of the kernel weights. Multiple Laplacians of the affinity weights endow our method with progressive detail decomposition of the input image from fine to coarse scale. These image components are blended by a structure mask, which avoids noise/artifact magnification or detail loss in the output image. Contributions of the proposed method to existing image editing tools are: (1) Low computational and memory requirements, making it appropriate for mobile device implementations (e.g. as a finish step in a camera pipeline), (2) A range of filtering applications from detail enhancement to denoising with only a few control parameters, enabling the user to apply a combination of various (and even opposite) filtering effects.
Tasks	Denoising
Published	2016-06-23
URL	http://arxiv.org/abs/1606.07396v1
PDF	http://arxiv.org/pdf/1606.07396v1.pdf
PWC	https://paperswithcode.com/paper/fast-multi-layer-laplacian-enhancement
Repo
Framework

Statistical Learning for OCR Text Correction


Title	Statistical Learning for OCR Text Correction
Authors	Jie Mei, Aminul Islam, Yajing Wu, Abidalrahman Moh’d, Evangelos E. Milios
Abstract	The accuracy of Optical Character Recognition (OCR) is crucial to the success of subsequent applications used in text analyzing pipeline. Recent models of OCR post-processing significantly improve the quality of OCR-generated text, but are still prone to suggest correction candidates from limited observations while insufficiently accounting for the characteristics of OCR errors. In this paper, we show how to enlarge candidate suggestion space by using external corpus and integrating OCR-specific features in a regression approach to correct OCR-generated errors. The evaluation results show that our model can correct 61.5% of the OCR-errors (considering the top 1 suggestion) and 71.5% of the OCR-errors (considering the top 3 suggestions), for cases where the theoretical correction upper-bound is 78%.
Tasks	Optical Character Recognition
Published	2016-11-21
URL	http://arxiv.org/abs/1611.06950v1
PDF	http://arxiv.org/pdf/1611.06950v1.pdf
PWC	https://paperswithcode.com/paper/statistical-learning-for-ocr-text-correction
Repo
Framework

Improved Achievability and Converse Bounds for Erdős-Rényi Graph Matching


Title	Improved Achievability and Converse Bounds for Erdős-Rényi Graph Matching
Authors	Daniel Cullina, Negar Kiyavash
Abstract	We consider the problem of perfectly recovering the vertex correspondence between two correlated Erd\H{o}s-R'enyi (ER) graphs. For a pair of correlated graphs on the same vertex set, the correspondence between the vertices can be obscured by randomly permuting the vertex labels of one of the graphs. In some cases, the structural information in the graphs allow this correspondence to be recovered. We investigate the information-theoretic threshold for exact recovery, i.e. the conditions under which the entire vertex correspondence can be correctly recovered given unbounded computational resources. Pedarsani and Grossglauser provided an achievability result of this type. Their result establishes the scaling dependence of the threshold on the number of vertices. We improve on their achievability bound. We also provide a converse bound, establishing conditions under which exact recovery is impossible. Together, these establish the scaling dependence of the threshold on the level of correlation between the two graphs. The converse and achievability bounds differ by a factor of two for sparse, significantly correlated graphs.
Tasks	Graph Matching
Published	2016-02-02
URL	http://arxiv.org/abs/1602.01042v1
PDF	http://arxiv.org/pdf/1602.01042v1.pdf
PWC	https://paperswithcode.com/paper/improved-achievability-and-converse-bounds
Repo
Framework

An integrated Graphical User Interface for Debugging Answer Set Programs


Title	An integrated Graphical User Interface for Debugging Answer Set Programs
Authors	Philip Gasteiger, Carmine Dodaro, Benjamin Musitsch, Kristian Reale, Francesco Ricca, Konstantin Schekotihin
Abstract	Answer Set Programming (ASP) is an expressive knowledge representation and reasoning framework. Due to its rather simple syntax paired with high-performance solvers, ASP is interesting for industrial applications. However, to err is human and thus debugging is an important activity during the development process. Therefore, tools for debugging non-ground answer set programs are needed. In this paper, we present a new graphical debugging interface for non-ground answer set programs. The tool is based on the recently-introduced DWASP approach for debugging and it simplifies the interaction with the debugger. Furthermore, the debugging interface is integrated in ASPIDE, a rich IDE for answer set programs. With our extension ASPIDE turns into a full-fledged IDE by offering debugging support.
Tasks
Published	2016-11-15
URL	http://arxiv.org/abs/1611.04969v1
PDF	http://arxiv.org/pdf/1611.04969v1.pdf
PWC	https://paperswithcode.com/paper/an-integrated-graphical-user-interface-for
Repo
Framework

A centralized reinforcement learning method for multi-agent job scheduling in Grid


Title	A centralized reinforcement learning method for multi-agent job scheduling in Grid
Authors	Milad Moradi
Abstract	One of the main challenges in Grid systems is designing an adaptive, scalable, and model-independent method for job scheduling to achieve a desirable degree of load balancing and system efficiency. Centralized job scheduling methods have some drawbacks, such as single point of failure and lack of scalability. Moreover, decentralized methods require a coordination mechanism with limited communications. In this paper, we propose a multi-agent approach to job scheduling in Grid, named Centralized Learning Distributed Scheduling (CLDS), by utilizing the reinforcement learning framework. The CLDS is a model free approach that uses the information of jobs and their completion time to estimate the efficiency of resources. In this method, there are a learner agent and several scheduler agents that perform the task of learning and job scheduling with the use of a coordination strategy that maintains the communication cost at a limited level. We evaluated the efficiency of the CLDS method by designing and performing a set of experiments on a simulated Grid system under different system scales and loads. The results show that the CLDS can effectively balance the load of system even in large scale and heavy loaded Grids, while maintains its adaptive performance and scalability.
Tasks
Published	2016-09-11
URL	http://arxiv.org/abs/1609.03157v1
PDF	http://arxiv.org/pdf/1609.03157v1.pdf
PWC	https://paperswithcode.com/paper/a-centralized-reinforcement-learning-method
Repo
Framework

Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?


Title	Human Attention in Visual Question Answering: Do Humans and Deep Networks Look at the Same Regions?
Authors	Abhishek Das, Harsh Agrawal, C. Lawrence Zitnick, Devi Parikh, Dhruv Batra
Abstract	We conduct large-scale studies on `human attention’ in Visual Question Answering (VQA) to understand where humans choose to look to answer questions about images. We design and test multiple game-inspired novel attention-annotation interfaces that require the subject to sharpen regions of a blurred image to answer a question. Thus, we introduce the VQA-HAT (Human ATtention) dataset. We evaluate attention maps generated by state-of-the-art VQA models against human attention both qualitatively (via visualizations) and quantitatively (via rank-order correlation). Overall, our experiments show that current attention models in VQA do not seem to be looking at the same regions as humans. \|
Tasks	Question Answering, Visual Question Answering
Published	2016-06-17
URL	http://arxiv.org/abs/1606.05589v1
PDF	http://arxiv.org/pdf/1606.05589v1.pdf
PWC	https://paperswithcode.com/paper/human-attention-in-visual-question-answering
Repo
Framework

A Self-Taught Artificial Agent for Multi-Physics Computational Model Personalization


Title	A Self-Taught Artificial Agent for Multi-Physics Computational Model Personalization
Authors	Dominik Neumann, Tommaso Mansi, Lucian Itu, Bogdan Georgescu, Elham Kayvanpour, Farbod Sedaghat-Hamedani, Ali Amr, Jan Haas, Hugo Katus, Benjamin Meder, Stefan Steidl, Joachim Hornegger, Dorin Comaniciu
Abstract	Personalization is the process of fitting a model to patient data, a critical step towards application of multi-physics computational models in clinical practice. Designing robust personalization algorithms is often a tedious, time-consuming, model- and data-specific process. We propose to use artificial intelligence concepts to learn this task, inspired by how human experts manually perform it. The problem is reformulated in terms of reinforcement learning. In an off-line phase, Vito, our self-taught artificial agent, learns a representative decision process model through exploration of the computational model: it learns how the model behaves under change of parameters. The agent then automatically learns an optimal strategy for on-line personalization. The algorithm is model-independent; applying it to a new model requires only adjusting few hyper-parameters of the agent and defining the observations to match. The full knowledge of the model itself is not required. Vito was tested in a synthetic scenario, showing that it could learn how to optimize cost functions generically. Then Vito was applied to the inverse problem of cardiac electrophysiology and the personalization of a whole-body circulation model. The obtained results suggested that Vito could achieve equivalent, if not better goodness of fit than standard methods, while being more robust (up to 11% higher success rates) and with faster (up to seven times) convergence rate. Our artificial intelligence approach could thus make personalization algorithms generalizable and self-adaptable to any patient and any model.
Tasks
Published	2016-05-01
URL	http://arxiv.org/abs/1605.00303v1
PDF	http://arxiv.org/pdf/1605.00303v1.pdf
PWC	https://paperswithcode.com/paper/a-self-taught-artificial-agent-for-multi
Repo
Framework

Multi-Subregion Based Correlation Filter Bank for Robust Face Recognition


Title	Multi-Subregion Based Correlation Filter Bank for Robust Face Recognition
Authors	Yan Yan, Hanzi Wang, David Suter
Abstract	In this paper, we propose an effective feature extraction algorithm, called Multi-Subregion based Correlation Filter Bank (MS-CFB), for robust face recognition. MS-CFB combines the benefits of global-based and local-based feature extraction algorithms, where multiple correlation filters correspond- ing to different face subregions are jointly designed to optimize the overall correlation outputs. Furthermore, we reduce the computational complexi- ty of MS-CFB by designing the correlation filter bank in the spatial domain and improve its generalization capability by capitalizing on the unconstrained form during the filter bank design process. MS-CFB not only takes the d- ifferences among face subregions into account, but also effectively exploits the discriminative information in face subregions. Experimental results on various public face databases demonstrate that the proposed algorithm pro- vides a better feature representation for classification and achieves higher recognition rates compared with several state-of-the-art algorithms.
Tasks	Face Recognition, Robust Face Recognition
Published	2016-03-24
URL	http://arxiv.org/abs/1603.07604v1
PDF	http://arxiv.org/pdf/1603.07604v1.pdf
PWC	https://paperswithcode.com/paper/multi-subregion-based-correlation-filter-bank
Repo
Framework

Tensor Based Second Order Variational Model for Image Reconstruction


Title	Tensor Based Second Order Variational Model for Image Reconstruction
Authors	Jinming Duan, Wil OC Ward, Luke Sibbett, Zhenkuan Pan, Li Bai
Abstract	Second order total variation (SOTV) models have advantages for image reconstruction over their first order counterparts including their ability to remove the staircase artefact in the reconstructed image, but they tend to blur the reconstructed image. To overcome this drawback, we introduce a new Tensor Weighted Second Order (TWSO) model for image reconstruction. Specifically, we develop a novel regulariser for the SOTV model that uses the Frobenius norm of the product of the SOTV Hessian matrix and the anisotropic tensor. We then adapt the alternating direction method of multipliers (ADMM) to solve the proposed model by breaking down the original problem into several subproblems. All the subproblems have closed-forms and can thus be solved efficiently. The proposed method is compared with a range of state-of-the-art approaches such as tensor-based anisotropic diffusion, total generalised variation, Euler’s elastica, etc. Numerical experimental results of the method on both synthetic and real images from the Berkeley database BSDS500 demonstrate that the proposed method eliminates both the staircase and blurring effects and outperforms the existing approaches for image inpainting and denoising applications.
Tasks	Denoising, Image Inpainting, Image Reconstruction
Published	2016-09-27
URL	http://arxiv.org/abs/1609.08387v1
PDF	http://arxiv.org/pdf/1609.08387v1.pdf
PWC	https://paperswithcode.com/paper/tensor-based-second-order-variational-model
Repo
Framework

L0-norm Sparse Graph-regularized SVD for Biclustering


Title	L0-norm Sparse Graph-regularized SVD for Biclustering
Authors	Wenwen Min, Juan Liu, Shihua Zhang
Abstract	Learning the “blocking” structure is a central challenge for high dimensional data (e.g., gene expression data). Recently, a sparse singular value decomposition (SVD) has been used as a biclustering tool to achieve this goal. However, this model ignores the structural information between variables (e.g., gene interaction graph). Although typical graph-regularized norm can incorporate such prior graph information to get accurate discovery and better interpretability, it fails to consider the opposite effect of variables with different signs. Motivated by the development of sparse coding and graph-regularized norm, we propose a novel sparse graph-regularized SVD as a powerful biclustering tool for analyzing high-dimensional data. The key of this method is to impose two penalties including a novel graph-regularized norm ($\pmb{u}\pmb{L}\pmb{u}$) and $L_0$-norm ($\pmb{u}_0$) on singular vectors to induce structural sparsity and enhance interpretability. We design an efficient Alternating Iterative Sparse Projection (AISP) algorithm to solve it. Finally, we apply our method and related ones to simulated and real data to show its efficiency in capturing natural blocking structures.
Tasks
Published	2016-03-19
URL	http://arxiv.org/abs/1603.06035v1
PDF	http://arxiv.org/pdf/1603.06035v1.pdf
PWC	https://paperswithcode.com/paper/l0-norm-sparse-graph-regularized-svd-for
Repo
Framework

Unsupervised Identification of Translationese


Title	Unsupervised Identification of Translationese
Authors	Ella Rabinovich, Shuly Wintner
Abstract	Translated texts are distinctively different from original ones, to the extent that supervised text classification methods can distinguish between them with high accuracy. These differences were proven useful for statistical machine translation. However, it has been suggested that the accuracy of translation detection deteriorates when the classifier is evaluated outside the domain it was trained on. We show that this is indeed the case, in a variety of evaluation scenarios. We then show that unsupervised classification is highly accurate on this task. We suggest a method for determining the correct labels of the clustering outcomes, and then use the labels for voting, improving the accuracy even further. Moreover, we suggest a simple method for clustering in the challenging case of mixed-domain datasets, in spite of the dominance of domain-related features over translation-related ones. The result is an effective, fully-unsupervised method for distinguishing between original and translated texts that can be applied to new domains with reasonable accuracy.
Tasks	Machine Translation, Text Classification
Published	2016-09-11
URL	http://arxiv.org/abs/1609.03205v1
PDF	http://arxiv.org/pdf/1609.03205v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-identification-of-translationese-1
Repo
Framework

Knowledge Transfer with Medical Language Embeddings


Title	Knowledge Transfer with Medical Language Embeddings
Authors	Stephanie L. Hyland, Theofanis Karaletsos, Gunnar Rätsch
Abstract	Identifying relationships between concepts is a key aspect of scientific knowledge synthesis. Finding these links often requires a researcher to laboriously search through scien- tific papers and databases, as the size of these resources grows ever larger. In this paper we describe how distributional semantics can be used to unify structured knowledge graphs with unstructured text to predict new relationships between medical concepts, using a probabilistic generative model. Our approach is also designed to ameliorate data sparsity and scarcity issues in the medical domain, which make language modelling more challenging. Specifically, we integrate the medical relational database (SemMedDB) with text from electronic health records (EHRs) to perform knowledge graph completion. We further demonstrate the ability of our model to predict relationships between tokens not appearing in the relational database.
Tasks	Knowledge Graph Completion, Knowledge Graphs, Language Modelling, Transfer Learning
Published	2016-02-10
URL	http://arxiv.org/abs/1602.03551v1
PDF	http://arxiv.org/pdf/1602.03551v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-transfer-with-medical-language
Repo
Framework

Data Poisoning Attacks on Factorization-Based Collaborative Filtering


Title	Data Poisoning Attacks on Factorization-Based Collaborative Filtering
Authors	Bo Li, Yining Wang, Aarti Singh, Yevgeniy Vorobeychik
Abstract	Recommendation and collaborative filtering systems are important in modern information and e-commerce applications. As these systems are becoming increasingly popular in the industry, their outputs could affect business decision making, introducing incentives for an adversarial party to compromise the availability or integrity of such systems. We introduce a data poisoning attack on collaborative filtering systems. We demonstrate how a powerful attacker with full knowledge of the learner can generate malicious data so as to maximize his/her malicious objectives, while at the same time mimicking normal user behavior to avoid being detected. While the complete knowledge assumption seems extreme, it enables a robust assessment of the vulnerability of collaborative filtering schemes to highly motivated attacks. We present efficient solutions for two popular factorization-based collaborative filtering algorithms: the \emph{alternative minimization} formulation and the \emph{nuclear norm minimization} method. Finally, we test the effectiveness of our proposed algorithms on real-world data and discuss potential defensive strategies.
Tasks	data poisoning, Decision Making
Published	2016-08-29
URL	http://arxiv.org/abs/1608.08182v2
PDF	http://arxiv.org/pdf/1608.08182v2.pdf
PWC	https://paperswithcode.com/paper/data-poisoning-attacks-on-factorization-based
Repo
Framework