Robust learning Bayesian networks for prior belief

Maomi Ueno
Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, PMLR R9:771-780, 2011.

Abstract

Recent reports have described that learning Bayesian networks are highly sensitive to the chosen equivalent sample size (ESS) in the Bayesian Dirichlet equivalence uniform (BDeu). This sensitivity often engenders some unstable or undesirable results. This paper describes some asymptotic analyses of BDeu to explain the reasons for the sensitivity and its effects. Furthermore, this paper presents a proposal for a robust learning score for ESS by eliminating the sensitive factors from the approximation of log-BDeu.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR9-ueno11a, title = {Robust learning {B}ayesian networks for prior belief}, author = {Ueno, Maomi}, booktitle = {Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence}, pages = {771--780}, year = {2011}, editor = {Cozman, Fabio and Pfeffer, Avi}, volume = {R9}, series = {Proceedings of Machine Learning Research}, month = {14--17 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r9/main/assets/ueno11a/ueno11a.pdf}, url = {https://proceedings.mlr.press/r9/ueno11a.html}, abstract = {Recent reports have described that learning Bayesian networks are highly sensitive to the chosen equivalent sample size (ESS) in the Bayesian Dirichlet equivalence uniform (BDeu). This sensitivity often engenders some unstable or undesirable results. This paper describes some asymptotic analyses of BDeu to explain the reasons for the sensitivity and its effects. Furthermore, this paper presents a proposal for a robust learning score for ESS by eliminating the sensitive factors from the approximation of log-BDeu.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Robust learning Bayesian networks for prior belief %A Maomi Ueno %B Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2011 %E Fabio Cozman %E Avi Pfeffer %F pmlr-vR9-ueno11a %I PMLR %P 771--780 %U https://proceedings.mlr.press/r9/ueno11a.html %V R9 %X Recent reports have described that learning Bayesian networks are highly sensitive to the chosen equivalent sample size (ESS) in the Bayesian Dirichlet equivalence uniform (BDeu). This sensitivity often engenders some unstable or undesirable results. This paper describes some asymptotic analyses of BDeu to explain the reasons for the sensitivity and its effects. Furthermore, this paper presents a proposal for a robust learning score for ESS by eliminating the sensitive factors from the approximation of log-BDeu. %Z Reissued by PMLR on 04 October 2026.
APA
Ueno, M.. (2011). Robust learning Bayesian networks for prior belief. Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R9:771-780 Available from https://proceedings.mlr.press/r9/ueno11a.html. Reissued by PMLR on 04 October 2026.

Related Material