Paper Info
Title
Exponential Family Tensor Factorization for Missing-Values Prediction and Anomaly Detection
Abstract
In this paper, we study probabilistic modeling of heterogeneously attributed multi-dimensional arrays. The model can manage the heterogeneity by employing an individual exponential-family distribution for each attribute of the tensor array. These entries are connected by latent variables and are shared information across the different attributes. Because a Bayesian inference for our model is intractable, we cast the EM algorithm approximated by using the Lap lace method and Gaussian process. This approximation enables us to derive a predictive distribution for missing values in a consistent manner. Simulation experiments show that our method outperforms other methods such as PARAFAC and Tucker decomposition in missing-values prediction for cross-national statistics and is also applicable to discover anomalies in heterogeneous office-logging data.
Year
DOI
Venue
2010
10.1109/ICDM.2010.39
Data Mining
Keywords
Field
DocType
Bayes methods,Gaussian processes,Laplace equations,belief networks,expectation-maximisation algorithm,inference mechanisms,matrix decomposition,prediction theory,sensor fusion,Bayesian inference,Gaussian process,Laplace method,anomaly detection,cross national statistic,exponential family tensor factorization,missing values prediction,multidimensional array,office logging data,probabilistic modeling,Bayesian probabilistic model,Gaussian process,data fusion,tensor factorization
Bayesian inference,Computer science,Expectation–maximization algorithm,Matrix decomposition,Exponential family,Laplace's method,Gaussian process,Artificial intelligence,Tucker decomposition,Missing data,Machine learning
Conference
ISSN
ISBN
Citations 
1550-4786 E-ISBN : 978-0-7695-4256-0
978-0-7695-4256-0
13
PageRank 
References 
Authors
0.64
19
4
Name
Order
Citations
PageRank
Hayashi, Kohei115915.31
Takashi Takenouchi218219.44
Tomohiro Shibata325649.49
Kamiya, Y.4130.98