Universidad de Granada Digibug

Repositorio Institucional de la Universidad de Granada >
1.-Investigación >
Departamentos, Grupos de Investigación e Institutos >
Departamento de Ciencias de la Computación e Inteligencia Artificial >
DCCIA - Artículos >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10481/32709

Title: A scoring function for learning Bayesian networks based on mutual information and conditional independence tests
Authors: Campos Ibáñez, Luis Miguel
Issue Date: 2006
Abstract: We propose a new scoring function for learning Bayesian networks from data using score+search algorithms. This is based on the concept of mutual information and exploits some well-known properties of this measure in a novel way. Essentially, a statistical independence test based on the chi-square distribution, associated with the mutual information measure, together with a property of additive decomposition of this measure, are combined in order to measure the degree of interaction between each variable and its parent variables in the network. The result is a non-Bayesian scoring function called MIT (mutual information tests) which belongs to the family of scores based on information theory. The MIT score also represents a penalization of the Kullback-Leibler divergence between the joint probability distributions associated with a candidate network and with the available data set. Detailed results of a complete experimental evaluation of the proposed scoring function and its comparison with the well-known K2, BDeu and BIC/MDL scores are also presented.
Sponsorship: I would like to acknowledge support for this work from the Spanish ‘Consejería de Innovación Ciencia y Empresa de la Junta de Andalucía’, under Project TIC-276.
Publisher: MIT Press
Keywords: Bayesian networks
Scoring functions
Mutual information
Conditional independence tests
URI: http://hdl.handle.net/10481/32709
ISSN: 1532-4435
Rights : Creative Commons Attribution-NonCommercial-NoDerivs 3.0 License
Citation: Campos, L.M. A scoring function for learning Bayesian networks based on mutual information and conditional independence tests. Journal of Machine Learning Research, 7: 2149-2187 (2006). [http://hdl.handle.net/10481/32709]
Appears in Collections:DCCIA - Artículos

Files in This Item:

File Description SizeFormat
Campos_LearningBayesianNetworks.pdf335.91 kBAdobe PDFView/Open
Recommend this item

This item is licensed under a Creative Commons License
Creative Commons

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0! OpenAire compliant DSpace Software Copyright © 2002-2007 MIT and Hewlett-Packard - Feedback

© Universidad de Granada