Infinite Tucker Decomposition: Nonparametric Bayesian Models for Multiway Data Analysis

Tensor decomposition is a powerful computational tool for multiway data analysis. Many popular tensor decomposition approaches---such as the Tucker decomposition and CANDECOMP/PARAFAC (CP)---amount to multi-linear factorization. They are insufficient to model (i) complex interactions between data entities, (ii) various data types (e.g. missing data and binary data), and (iii) noisy observations and outliers. To address these issues, we propose tensor-variate latent nonparametric Bayesian models, coupled with efficient inference methods, for multiway data analysis. We name these models InfTucker. Using these InfTucker, we conduct Tucker decomposition in an infinite feature space. Unlike classical tensor decomposition models, our new approaches handle both continuous and binary data in a probabilistic framework. Unlike previous Bayesian models on matrices and tensors, our models are based on latent Gaussian or $t$ processes with nonlinear covariance functions. To efficiently learn the InfTucker from data, we develop a variational inference technique on tensors. Compared with classical implementation, the new technique reduces both time and space complexities by several orders of magnitude. Our experimental results on chemometrics and social network datasets demonstrate that our new models achieved significantly higher prediction accuracy than the most state-of-art tensor decomposition

[1]  L. Tucker,et al.  Some mathematical notes on three-mode factor analysis , 1966, Psychometrika.

[2]  Wei Chu,et al.  Probabilistic Models for Incomplete Multi-dimensional Arrays , 2009, AISTATS.

[3]  Zenglin Xu,et al.  Sparse matrix-variate Gaussian process blockmodels for network modeling , 2011, UAI.

[4]  Max Welling,et al.  Multi-HDP: A Non Parametric Bayesian Model for Tensor Factorization , 2008, AAAI.

[5]  Walter Willinger,et al.  Spatio-temporal compressive sensing and internet traffic matrices , 2009, SIGCOMM '09.

[6]  Dit-Yan Yeung,et al.  Multi-Task Learning using Generalized t Process , 2010, AISTATS.

[7]  Wei Chu,et al.  Gaussian Process Models for Link Analysis and Transfer Learning , 2007, NIPS.

[8]  Neil D. Lawrence,et al.  Semi-supervised Learning via Gaussian Processes , 2004, NIPS.

[9]  Wei Chu,et al.  Stochastic Relational Models for Discriminative Link Prediction , 2006, NIPS.

[10]  Peter D. Hoff,et al.  Hierarchical multilinear models for multiway data , 2010, Comput. Stat. Data Anal..

[11]  S. Chib,et al.  Bayesian analysis of binary and polychotomous response data , 1993 .

[12]  Tamir Hazan,et al.  Non-negative tensor factorization with applications to statistics and computer vision , 2005, ICML.

[13]  Seungjin Choi,et al.  Nonnegative Tucker Decomposition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  A. Rukhin Matrix Variate Distributions , 1999, The Multivariate Normal Distribution.

[15]  Xi Chen,et al.  Temporal Collaborative Filtering with Bayesian Probabilistic Tensor Factorization , 2010, SDM.

[16]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[17]  Jieping Ye,et al.  Matrix-variate and higher-order probabilistic projections , 2011, Data Mining and Knowledge Discovery.

[18]  Tamara G. Kolda,et al.  Scalable Tensor Factorizations for Incomplete Data , 2010, ArXiv.

[19]  Jimeng Sun,et al.  MultiVis: Content-Based Social Network Exploration through Multi-way Visual Analysis , 2009, SDM.

[20]  Jimeng Sun,et al.  Beyond streams and graphs: dynamic tensor analysis , 2006, KDD '06.

[21]  Richard A. Harshman,et al.  Foundations of the PARAFAC procedure: Models and conditions for an "explanatory" multi-model factor analysis , 1970 .

[22]  Edwin V. Bonilla,et al.  Multi-task Gaussian Process Prediction , 2007, NIPS.

[23]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[24]  Jimeng Sun,et al.  MetaFac: community discovery via relational hypergraph factorization , 2009, KDD.

[25]  Joos Vandewalle,et al.  A Multilinear Singular Value Decomposition , 2000, SIAM J. Matrix Anal. Appl..

[26]  Michael E. Tipping,et al.  Probabilistic Principal Component Analysis , 1999 .