Traditionally, the task of learning Bayesian Networks (BNs) from data
has been treated as a NP-Hard search problem. To overcome such difficulty
in terms of computational complexity, several approximations have
been designed, such as imposing a previous ordering on the domain
attributes that restrict the number of Bayesian structures to be
learned or using other approaches trying to reduce the state space
of this problem. In this paper, we propose a simple method based
on feature ranking algorithms which has low computational complexity
(O(n2), where n is the number of variables) and produces good results.
We empirically demonstrate that feature ranking algorithms (namely,
Chi-Squared and Information Gain) can be used to define efficient
variables ordering in the BNC learning context. The proposed method
can bring improvements, when using the K2 algorithm, to learn a Bayesian
Network Classifier from data.
%0 Journal Article
%1 Jr.2007
%A Jr., Estevam R. Hruschka
%A Ebecken, Nelson F.F.
%D 2007
%J Data & Knowledge Engineering
%K Bayesian classifiers networks
%N 2
%P 258 - 269
%R DOI: 10.1016/j.datak.2007.02.003
%T Towards efficient variables ordering for Bayesian networks classifier
%U http://www.sciencedirect.com/science/article/B6TYX-4N6FFGS-1/2/e0212a3957a9f96b80430c454a223ed5
%V 63
%X Traditionally, the task of learning Bayesian Networks (BNs) from data
has been treated as a NP-Hard search problem. To overcome such difficulty
in terms of computational complexity, several approximations have
been designed, such as imposing a previous ordering on the domain
attributes that restrict the number of Bayesian structures to be
learned or using other approaches trying to reduce the state space
of this problem. In this paper, we propose a simple method based
on feature ranking algorithms which has low computational complexity
(O(n2), where n is the number of variables) and produces good results.
We empirically demonstrate that feature ranking algorithms (namely,
Chi-Squared and Information Gain) can be used to define efficient
variables ordering in the BNC learning context. The proposed method
can bring improvements, when using the K2 algorithm, to learn a Bayesian
Network Classifier from data.
@article{Jr.2007,
abstract = {Traditionally, the task of learning Bayesian Networks (BNs) from data
has been treated as a NP-Hard search problem. To overcome such difficulty
in terms of computational complexity, several approximations have
been designed, such as imposing a previous ordering on the domain
attributes that restrict the number of Bayesian structures to be
learned or using other approaches trying to reduce the state space
of this problem. In this paper, we propose a simple method based
on feature ranking algorithms which has low computational complexity
(O(n2), where n is the number of variables) and produces good results.
We empirically demonstrate that feature ranking algorithms (namely,
Chi-Squared and Information Gain) can be used to define efficient
variables ordering in the BNC learning context. The proposed method
can bring improvements, when using the K2 algorithm, to learn a Bayesian
Network Classifier from data.},
added-at = {2009-09-12T19:19:34.000+0200},
author = {Jr., Estevam R. Hruschka and Ebecken, Nelson F.F.},
biburl = {https://www.bibsonomy.org/bibtex/2c04c9ae61129fe377d9aa71daf531c60/mozaher},
doi = {DOI: 10.1016/j.datak.2007.02.003},
file = {:Jr.2007.pdf:PDF},
interhash = {8ada0cf4b316d054e593f95f80a1e034},
intrahash = {c04c9ae61129fe377d9aa71daf531c60},
issn = {0169-023X},
journal = {Data \& Knowledge Engineering},
keywords = {Bayesian classifiers networks},
number = 2,
owner = {Mozaherul Hoque},
pages = {258 - 269},
timestamp = {2009-09-12T19:19:40.000+0200},
title = {Towards efficient variables ordering for Bayesian networks classifier},
url = {http://www.sciencedirect.com/science/article/B6TYX-4N6FFGS-1/2/e0212a3957a9f96b80430c454a223ed5},
volume = 63,
year = 2007
}