Title :
Bayesian Model Averaging of Naive Bayes for Clustering
Author :
Santafé, Guzmán ; Lozano, Jose A. ; Larranaga, Pedro
Author_Institution :
Dept. of Comput. Sci. & Artificial Intelligence, Univ. of the Basque Country
Abstract :
This paper considers a Bayesian model-averaging (MA) approach to learn an unsupervised naive Bayes classification model. By using the expectation model-averaging (EMA) algorithm, which is proposed in this paper, a unique naive Bayes model that approximates an MA over selective naive Bayes structures is obtained. This algorithm allows to obtain the parameters for the approximate MA clustering model in the same time complexity needed to learn the maximum-likelihood model with the expectation-maximization algorithm. On the other hand, the proposed method can also be regarded as an approach to an unsupervised feature subset selection due to the fact that the model obtained by the EMA algorithm incorporates information on how dependent every predictive variable is on the cluster variable
Keywords :
Bayes methods; computational complexity; expectation-maximisation algorithm; learning (artificial intelligence); pattern classification; pattern clustering; Bayesian model averaging; expectation model-averaging; expectation-maximization algorithm; maximum-likelihood model; pattern clustering; time complexity; unsupervised feature subset selection; unsupervised naive Bayes classification model; Artificial intelligence; Bayesian methods; Clustering algorithms; Government; Intelligent systems; Partitioning algorithms; Predictive models; Probability distribution; Tin; Uncertainty; Bayesian model averaging (MA); clustering; expectation–maximization (EM); naive Bayes;
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
DOI :
10.1109/TSMCB.2006.874132
