Learning Bayesian Networks From Dependency Networks: A Preliminary Study

Geoff Hulten, David Maxwell Chickering, David Heckerman
Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, PMLR R4:141-148, 2003.

Abstract

In this paper we describe how to learn Bayesian networks from a summary of complete data in the form of a dependency network rather than from data directly. This method allows us to gain the advantages of both representations: scalable algorithms for learning dependency networks and convenient inference with Bayesian networks. Our approach is to use a dependency network as an "oracle" for the statistics needed to learn a Bayesian network. We show that the general problem is NP-hard and develop a greedy search algorithm. We conduct a preliminary experimental evaluation and find that the prediction accuracy of the Bayesian networks constructed from our algorithm almost equals that of Bayesian networks learned directly from the data.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR4-hulten03a, title = {Learning Bayesian Networks From Dependency Networks: {A} Preliminary Study}, author = {Hulten, Geoff and Chickering, David Maxwell and Heckerman, David}, booktitle = {Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics}, pages = {141--148}, year = {2003}, editor = {Bishop, Christopher M. and Frey, Brendan J.}, volume = {R4}, series = {Proceedings of Machine Learning Research}, month = {03--06 Jan}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/r4/hulten03a/hulten03a.pdf}, url = {https://proceedings.mlr.press/r4/hulten03a.html}, abstract = {In this paper we describe how to learn Bayesian networks from a summary of complete data in the form of a dependency network rather than from data directly. This method allows us to gain the advantages of both representations: scalable algorithms for learning dependency networks and convenient inference with Bayesian networks. Our approach is to use a dependency network as an "oracle" for the statistics needed to learn a Bayesian network. We show that the general problem is NP-hard and develop a greedy search algorithm. We conduct a preliminary experimental evaluation and find that the prediction accuracy of the Bayesian networks constructed from our algorithm almost equals that of Bayesian networks learned directly from the data.}, note = {Reissued by PMLR on 01 April 2021.} }
Endnote
%0 Conference Paper %T Learning Bayesian Networks From Dependency Networks: A Preliminary Study %A Geoff Hulten %A David Maxwell Chickering %A David Heckerman %B Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2003 %E Christopher M. Bishop %E Brendan J. Frey %F pmlr-vR4-hulten03a %I PMLR %P 141--148 %U https://proceedings.mlr.press/r4/hulten03a.html %V R4 %X In this paper we describe how to learn Bayesian networks from a summary of complete data in the form of a dependency network rather than from data directly. This method allows us to gain the advantages of both representations: scalable algorithms for learning dependency networks and convenient inference with Bayesian networks. Our approach is to use a dependency network as an "oracle" for the statistics needed to learn a Bayesian network. We show that the general problem is NP-hard and develop a greedy search algorithm. We conduct a preliminary experimental evaluation and find that the prediction accuracy of the Bayesian networks constructed from our algorithm almost equals that of Bayesian networks learned directly from the data. %Z Reissued by PMLR on 01 April 2021.
APA
Hulten, G., Chickering, D.M. & Heckerman, D.. (2003). Learning Bayesian Networks From Dependency Networks: A Preliminary Study. Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research R4:141-148 Available from https://proceedings.mlr.press/r4/hulten03a.html. Reissued by PMLR on 01 April 2021.

Related Material