Flexible learning of k-dependence Bayesian network classifiers

Conference item

In this paper we present an extension to the classical kdependence Bayesian network classifier algorithm. The original method intends to work for the whole continuum of Bayesian classifiers, from na¨ıve Bayes to unrestricted networks. In our experience, it performs well for low values of k. However, the algorithm tends to degrade in more complex spaces, as it greedily tries to add k dependencies to all feature nodes of the resulting net. We try to overcome this limitation by seeking for optimal values of k on a feature per feature basis. At the same time, we look for the best feature ordering. That is, we try to estimate the joint probability distribution of optimal feature orderings and individual number of dependencies. We feel that this preserves the essence of the original algorithm, while providing notable performance improvements.

Authors: García, AR; Gámez, JA

• Publication status: Published
• Publisher: ACM Press
• Host title: Proceedings of the 13th annual conference on Genetic and evolutionary computation - GECCO '11
• Publication date: 2011-01-01
• Event title: the 13th annual conference
• Event location: Dublin,, Ireland
• Event start date: 2011-07-12
• Event end date: 2011-07-16
• DOI: 10.1145/2001576.2001741
• ISBN: 9781450305570
• Language: © The authors
• Keywords: SBTMR