Scoring and Searching over Bayesian Networks with Causal and Associative Priors

Giorgos Borboudakis, Ioannis Tsamardinos
Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence, PMLR R11:322-331, 2013.

Abstract

A significant theoretical advantage of search- and-score methods for learning Bayesian Net- works is that they can accept informative prior beliefs for each possible network, thus complementing the data. In this paper, a method is presented for assigning priors based on beliefs on the presence or absence of certain paths in the true network. Such be- liefs correspond to knowledge about the pos- sible causal and associative relations between pairs of variables. This type of knowledge naturally arises from prior experimental and observational data, among others. In addi- tion, a novel search-operator is proposed to take advantage of such prior knowledge. Ex- periments show that, using path beliefs im- proves the learning of the skeleton, as well as the edge directions in the network.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR11-borboudakis13a, title = {Scoring and Searching over {B}ayesian Networks with Causal and Associative Priors}, author = {Borboudakis, Giorgos and Tsamardinos, Ioannis}, booktitle = {Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence}, pages = {322--331}, year = {2013}, editor = {Nicholson, Ann and Smyth, Padhraic}, volume = {R11}, series = {Proceedings of Machine Learning Research}, month = {12--14 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r11/main/assets/borboudakis13a/borboudakis13a.pdf}, url = {https://proceedings.mlr.press/r11/borboudakis13a.html}, abstract = {A significant theoretical advantage of search- and-score methods for learning Bayesian Net- works is that they can accept informative prior beliefs for each possible network, thus complementing the data. In this paper, a method is presented for assigning priors based on beliefs on the presence or absence of certain paths in the true network. Such be- liefs correspond to knowledge about the pos- sible causal and associative relations between pairs of variables. This type of knowledge naturally arises from prior experimental and observational data, among others. In addi- tion, a novel search-operator is proposed to take advantage of such prior knowledge. Ex- periments show that, using path beliefs im- proves the learning of the skeleton, as well as the edge directions in the network.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Scoring and Searching over Bayesian Networks with Causal and Associative Priors %A Giorgos Borboudakis %A Ioannis Tsamardinos %B Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2013 %E Ann Nicholson %E Padhraic Smyth %F pmlr-vR11-borboudakis13a %I PMLR %P 322--331 %U https://proceedings.mlr.press/r11/borboudakis13a.html %V R11 %X A significant theoretical advantage of search- and-score methods for learning Bayesian Net- works is that they can accept informative prior beliefs for each possible network, thus complementing the data. In this paper, a method is presented for assigning priors based on beliefs on the presence or absence of certain paths in the true network. Such be- liefs correspond to knowledge about the pos- sible causal and associative relations between pairs of variables. This type of knowledge naturally arises from prior experimental and observational data, among others. In addi- tion, a novel search-operator is proposed to take advantage of such prior knowledge. Ex- periments show that, using path beliefs im- proves the learning of the skeleton, as well as the edge directions in the network. %Z Reissued by PMLR on 04 October 2026.
APA
Borboudakis, G. & Tsamardinos, I.. (2013). Scoring and Searching over Bayesian Networks with Causal and Associative Priors. Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R11:322-331 Available from https://proceedings.mlr.press/r11/borboudakis13a.html. Reissued by PMLR on 04 October 2026.

Related Material