Bayesian Model Averaging of Naive Bayes for Clustering. Santafé, G., Lozano, J., & Larranaga, P. IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics), 36(5):1149-1161, 10, 2006.
Bayesian Model Averaging of Naive Bayes for Clustering [link]Website  abstract   bibtex   
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
@article{
 title = {Bayesian Model Averaging of Naive Bayes for Clustering},
 type = {article},
 year = {2006},
 identifiers = {[object Object]},
 pages = {1149-1161},
 volume = {36},
 websites = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1703656},
 month = {10},
 id = {3f03fac9-391e-3f75-9fa0-0924568ec411},
 created = {2018-01-30T08:13:09.008Z},
 accessed = {2011-01-14},
 file_attached = {false},
 profile_id = {9fa698af-5b25-37c6-bbb8-e1b3cd831ec2},
 group_id = {165bb104-ad0f-3683-906f-c36a29c720bb},
 last_modified = {2018-01-30T08:13:09.008Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {santafe2006},
 private_publication = {false},
 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},
 bibtype = {article},
 author = {Santafé, G. and Lozano, J.A. and Larranaga, P.},
 journal = {IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics)},
 number = {5}
}

Downloads: 0