Instance-Specific Bayesian Network Structure Learning

Fattaneh Jabbari, Shyam Visweswaran, Gregory F. Cooper
Proceedings of the Ninth International Conference on Probabilistic Graphical Models, PMLR 72:169-180, 2018.

Abstract

Bayesian network (BN) structure learning algorithms are almost always designed to recover the structure that models \textit{the relationships that are shared by the instances in a population}. While accurately learning such population-wide Bayesian networks is useful, learning Bayesian networks that are specific to each instance is often important as well. For example, to understand and treat a patient (instance), it is critical to understand the specific causal mechanisms that are operating in that particular patient. We introduce an instance-specific BN structure learning method that searches the space of Bayesian networks to build a model that is specific to an instance by guiding the search based on attributes of the given instance (e.g., patient symptoms, signs, lab results, and genotype). The structure discovery performance of the proposed method is compared to an existing state-of-the-art BN structure learning method, namely an implementation of the Greedy Equivalence Search algorithm called FGES, using both simulated and real data. The results show that the proposed method improves the precision of the model structure that is output, when compared to GES, especially for those variables that exhibit context-specific independence.

Cite this Paper


BibTeX
@InProceedings{pmlr-v72-jabbari18a, title = {Instance-Specific Bayesian Network Structure Learning}, author = {Jabbari, Fattaneh and Visweswaran, Shyam and Cooper, Gregory F.}, booktitle = {Proceedings of the Ninth International Conference on Probabilistic Graphical Models}, pages = {169--180}, year = {2018}, editor = {Kratochvíl, Václav and Studený, Milan}, volume = {72}, series = {Proceedings of Machine Learning Research}, month = {11--14 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v72/jabbari18a/jabbari18a.pdf}, url = {https://proceedings.mlr.press/v72/jabbari18a.html}, abstract = {Bayesian network (BN) structure learning algorithms are almost always designed to recover the structure that models \textit{the relationships that are shared by the instances in a population}. While accurately learning such population-wide Bayesian networks is useful, learning Bayesian networks that are specific to each instance is often important as well. For example, to understand and treat a patient (instance), it is critical to understand the specific causal mechanisms that are operating in that particular patient. We introduce an instance-specific BN structure learning method that searches the space of Bayesian networks to build a model that is specific to an instance by guiding the search based on attributes of the given instance (e.g., patient symptoms, signs, lab results, and genotype). The structure discovery performance of the proposed method is compared to an existing state-of-the-art BN structure learning method, namely an implementation of the Greedy Equivalence Search algorithm called FGES, using both simulated and real data. The results show that the proposed method improves the precision of the model structure that is output, when compared to GES, especially for those variables that exhibit context-specific independence.} }
Endnote
%0 Conference Paper %T Instance-Specific Bayesian Network Structure Learning %A Fattaneh Jabbari %A Shyam Visweswaran %A Gregory F. Cooper %B Proceedings of the Ninth International Conference on Probabilistic Graphical Models %C Proceedings of Machine Learning Research %D 2018 %E Václav Kratochvíl %E Milan Studený %F pmlr-v72-jabbari18a %I PMLR %P 169--180 %U https://proceedings.mlr.press/v72/jabbari18a.html %V 72 %X Bayesian network (BN) structure learning algorithms are almost always designed to recover the structure that models \textit{the relationships that are shared by the instances in a population}. While accurately learning such population-wide Bayesian networks is useful, learning Bayesian networks that are specific to each instance is often important as well. For example, to understand and treat a patient (instance), it is critical to understand the specific causal mechanisms that are operating in that particular patient. We introduce an instance-specific BN structure learning method that searches the space of Bayesian networks to build a model that is specific to an instance by guiding the search based on attributes of the given instance (e.g., patient symptoms, signs, lab results, and genotype). The structure discovery performance of the proposed method is compared to an existing state-of-the-art BN structure learning method, namely an implementation of the Greedy Equivalence Search algorithm called FGES, using both simulated and real data. The results show that the proposed method improves the precision of the model structure that is output, when compared to GES, especially for those variables that exhibit context-specific independence.
APA
Jabbari, F., Visweswaran, S. & Cooper, G.F.. (2018). Instance-Specific Bayesian Network Structure Learning. Proceedings of the Ninth International Conference on Probabilistic Graphical Models, in Proceedings of Machine Learning Research 72:169-180 Available from https://proceedings.mlr.press/v72/jabbari18a.html.

Related Material