On Intercausal Interactions in Probabilistic Relational Models

Silja Renooij, Linda C. van der Gaag, Philippe Leray
Proceedings of the Eleventh International Symposium on Imprecise Probabilities: Theories and Applications, PMLR 103:327-329, 2019.

Abstract

Probabilistic relational models (PRMs) extend Bayesian networks beyond propositional expressiveness by allowing the representation of multiple interacting classes. For a specific instance of sets of concrete objects per class, a ground Bayesian network is composed by replicating parts of the PRM. The interactions between the objects that are thereby induced, are not always obvious from the PRM. We demonstrate in this paper that the replicative structure of the ground network in fact constrains the space of possible probability distributions and thereby the possible patterns of intercausal interaction.

Cite this Paper


BibTeX
@InProceedings{pmlr-v103-renooij19a, title = {On Intercausal Interactions in Probabilistic Relational Models}, author = {Renooij, Silja and {van der Gaag}, Linda C. and Leray, Philippe}, booktitle = {Proceedings of the Eleventh International Symposium on Imprecise Probabilities: Theories and Applications}, pages = {327--329}, year = {2019}, editor = {De Bock, Jasper and de Campos, Cassio P. and de Cooman, Gert and Quaeghebeur, Erik and Wheeler, Gregory}, volume = {103}, series = {Proceedings of Machine Learning Research}, month = {03--06 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v103/renooij19a/renooij19a.pdf}, url = {http://proceedings.mlr.press/v103/renooij19a.html}, abstract = {Probabilistic relational models (PRMs) extend Bayesian networks beyond propositional expressiveness by allowing the representation of multiple interacting classes. For a specific instance of sets of concrete objects per class, a ground Bayesian network is composed by replicating parts of the PRM. The interactions between the objects that are thereby induced, are not always obvious from the PRM. We demonstrate in this paper that the replicative structure of the ground network in fact constrains the space of possible probability distributions and thereby the possible patterns of intercausal interaction.} }
Endnote
%0 Conference Paper %T On Intercausal Interactions in Probabilistic Relational Models %A Silja Renooij %A Linda C. van der Gaag %A Philippe Leray %B Proceedings of the Eleventh International Symposium on Imprecise Probabilities: Theories and Applications %C Proceedings of Machine Learning Research %D 2019 %E Jasper De Bock %E Cassio P. de Campos %E Gert de Cooman %E Erik Quaeghebeur %E Gregory Wheeler %F pmlr-v103-renooij19a %I PMLR %P 327--329 %U http://proceedings.mlr.press/v103/renooij19a.html %V 103 %X Probabilistic relational models (PRMs) extend Bayesian networks beyond propositional expressiveness by allowing the representation of multiple interacting classes. For a specific instance of sets of concrete objects per class, a ground Bayesian network is composed by replicating parts of the PRM. The interactions between the objects that are thereby induced, are not always obvious from the PRM. We demonstrate in this paper that the replicative structure of the ground network in fact constrains the space of possible probability distributions and thereby the possible patterns of intercausal interaction.
APA
Renooij, S., van der Gaag, L.C. & Leray, P.. (2019). On Intercausal Interactions in Probabilistic Relational Models. Proceedings of the Eleventh International Symposium on Imprecise Probabilities: Theories and Applications, in Proceedings of Machine Learning Research 103:327-329 Available from http://proceedings.mlr.press/v103/renooij19a.html.

Related Material