Relevance for Robust Bayesian Network MAP-Explanations

Silja Renooij
Proceedings of The 11th International Conference on Probabilistic Graphical Models, PMLR 186:13-24, 2022.

Abstract

In the context of explainable AI, the concept of MAP-independence was recently introduced as a means for conveying the (ir)relevance of intermediate nodes for MAP computations in Bayesian networks. In this paper, we further study the concept of MAP-independence, discuss methods for finding sets of relevant nodes, and suggest ways to use these in providing users with an explanation concerning the robustness of the MAP result.

Cite this Paper

BibTeX
@InProceedings{pmlr-v186-renooij22a, title = {Relevance for Robust {B}ayesian Network {MAP}-Explanations}, author = {Renooij, Silja}, booktitle = {Proceedings of The 11th International Conference on Probabilistic Graphical Models}, pages = {13--24}, year = {2022}, editor = {Salmerón, Antonio and Rumı́, Rafael}, volume = {186}, series = {Proceedings of Machine Learning Research}, month = {05--07 Oct}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v186/renooij22a/renooij22a.pdf}, url = {https://proceedings.mlr.press/v186/renooij22a.html}, abstract = {In the context of explainable AI, the concept of MAP-independence was recently introduced as a means for conveying the (ir)relevance of intermediate nodes for MAP computations in Bayesian networks. In this paper, we further study the concept of MAP-independence, discuss methods for finding sets of relevant nodes, and suggest ways to use these in providing users with an explanation concerning the robustness of the MAP result.} }
Endnote
%0 Conference Paper %T Relevance for Robust Bayesian Network MAP-Explanations %A Silja Renooij %B Proceedings of The 11th International Conference on Probabilistic Graphical Models %C Proceedings of Machine Learning Research %D 2022 %E Antonio Salmerón %E Rafael Rumı́ %F pmlr-v186-renooij22a %I PMLR %P 13--24 %U https://proceedings.mlr.press/v186/renooij22a.html %V 186 %X In the context of explainable AI, the concept of MAP-independence was recently introduced as a means for conveying the (ir)relevance of intermediate nodes for MAP computations in Bayesian networks. In this paper, we further study the concept of MAP-independence, discuss methods for finding sets of relevant nodes, and suggest ways to use these in providing users with an explanation concerning the robustness of the MAP result.
APA
Renooij, S.. (2022). Relevance for Robust Bayesian Network MAP-Explanations. Proceedings of The 11th International Conference on Probabilistic Graphical Models, in Proceedings of Machine Learning Research 186:13-24 Available from https://proceedings.mlr.press/v186/renooij22a.html.

Related Material