Formal Verification of Bayesian Network Classifiers
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
Text
Shih et al. "Formal Verification of Bayesian Network Classifiers." Proceedings of the Ninth International Conference on Probabilistic Graphical Models, 2018.Markdown
[Shih et al. "Formal Verification of Bayesian Network Classifiers." Proceedings of the Ninth International Conference on Probabilistic Graphical Models, 2018.](https://mlanthology.org/pgm/2018/shih2018pgm-formal/)BibTeX
@inproceedings{shih2018pgm-formal,
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},
year = {2018},
pages = {427-438},
volume = {72},
url = {https://mlanthology.org/pgm/2018/shih2018pgm-formal/}
}