Formal Verification of Bayesian Network Classifiers

Andy Shih, Arthur Choi, Adnan Darwiche
; Proceedings of the Ninth International Conference on Probabilistic Graphical Models, PMLR 72:427-438, 2018.

Abstract

A new approach was recently proposed for {\em explaining} the decisions made by Bayesian network classifiers. This approach is based on first compiling a given classifier (i.e., its decision function) into a tractable representation called an Ordered Decision Diagram (ODD). Given an ODD representation of the decision function, we get the ability to provide reasons for why a classifier labels a given instance positively or negatively. We show in this paper that this approach also gives us the ability to {\em verify} the behavior of classifiers. We also provide case studies in explaining and verifying classifiers for some real-world domains, such as in medical diagnosis and educational assessment.

Cite this Paper


BibTeX
@InProceedings{pmlr-v72-shih18a, title = {Formal Verification of Bayesian Network Classifiers}, author = {Shih, Andy and Choi, Arthur and Darwiche, Adnan}, booktitle = {Proceedings of the Ninth International Conference on Probabilistic Graphical Models}, pages = {427--438}, year = {2018}, editor = {Václav Kratochvíl and Milan Studený}, volume = {72}, series = {Proceedings of Machine Learning Research}, address = {Prague, Czech Republic}, month = {11--14 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v72/shih18a/shih18a.pdf}, url = {http://proceedings.mlr.press/v72/shih18a.html}, abstract = {A new approach was recently proposed for {\em explaining} the decisions made by Bayesian network classifiers. This approach is based on first compiling a given classifier (i.e., its decision function) into a tractable representation called an Ordered Decision Diagram (ODD). Given an ODD representation of the decision function, we get the ability to provide reasons for why a classifier labels a given instance positively or negatively. We show in this paper that this approach also gives us the ability to {\em verify} the behavior of classifiers. We also provide case studies in explaining and verifying classifiers for some real-world domains, such as in medical diagnosis and educational assessment.} }
Endnote
%0 Conference Paper %T Formal Verification of Bayesian Network Classifiers %A Andy Shih %A Arthur Choi %A Adnan Darwiche %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-shih18a %I PMLR %J Proceedings of Machine Learning Research %P 427--438 %U http://proceedings.mlr.press %V 72 %W PMLR %X A new approach was recently proposed for {\em explaining} the decisions made by Bayesian network classifiers. This approach is based on first compiling a given classifier (i.e., its decision function) into a tractable representation called an Ordered Decision Diagram (ODD). Given an ODD representation of the decision function, we get the ability to provide reasons for why a classifier labels a given instance positively or negatively. We show in this paper that this approach also gives us the ability to {\em verify} the behavior of classifiers. We also provide case studies in explaining and verifying classifiers for some real-world domains, such as in medical diagnosis and educational assessment.
APA
Shih, A., Choi, A. & Darwiche, A.. (2018). Formal Verification of Bayesian Network Classifiers. Proceedings of the Ninth International Conference on Probabilistic Graphical Models, in PMLR 72:427-438

Related Material