Explanation trees for causal Bayesian networks

Ulf H. Nielsen, Jean-Philippe Pellet, André Elisseeff
Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence, PMLR R6:427-434, 2008.

Abstract

Bayesian networks can be used to extract explanations about the observed state of a subset of variables. In this paper, we explicate the desiderata of an explanation and confront them with the concept of explanation proposed by existing methods. The necessity of taking into account causal approaches when sal graph is available is discussed. We then introduce causal explanation trees, based on the construction of explanation trees using the measure of causal information flow (Ay and Polani, 2006). This approach is compared to several other methods on known networks.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR6-nielsen08a, title = {Explanation trees for causal Bayesian networks}, author = {Nielsen, Ulf H. and Pellet, Jean-Philippe and Elisseeff, Andr\'{e}}, booktitle = {Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence}, pages = {427--434}, year = {2008}, editor = {McAllester, David A. and Myllymäki, Petri}, volume = {R6}, series = {Proceedings of Machine Learning Research}, month = {09--12 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r6/main/assets/nielsen08a/nielsen08a.pdf}, url = {https://proceedings.mlr.press/r6/nielsen08a.html}, abstract = {Bayesian networks can be used to extract explanations about the observed state of a subset of variables. In this paper, we explicate the desiderata of an explanation and confront them with the concept of explanation proposed by existing methods. The necessity of taking into account causal approaches when sal graph is available is discussed. We then introduce causal explanation trees, based on the construction of explanation trees using the measure of causal information flow (Ay and Polani, 2006). This approach is compared to several other methods on known networks.}, note = {Reissued by PMLR on 09 October 2024.} }
Endnote
%0 Conference Paper %T Explanation trees for causal Bayesian networks %A Ulf H. Nielsen %A Jean-Philippe Pellet %A André Elisseeff %B Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2008 %E David A. McAllester %E Petri Myllymäki %F pmlr-vR6-nielsen08a %I PMLR %P 427--434 %U https://proceedings.mlr.press/r6/nielsen08a.html %V R6 %X Bayesian networks can be used to extract explanations about the observed state of a subset of variables. In this paper, we explicate the desiderata of an explanation and confront them with the concept of explanation proposed by existing methods. The necessity of taking into account causal approaches when sal graph is available is discussed. We then introduce causal explanation trees, based on the construction of explanation trees using the measure of causal information flow (Ay and Polani, 2006). This approach is compared to several other methods on known networks. %Z Reissued by PMLR on 09 October 2024.
APA
Nielsen, U.H., Pellet, J. & Elisseeff, A.. (2008). Explanation trees for causal Bayesian networks. Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R6:427-434 Available from https://proceedings.mlr.press/r6/nielsen08a.html. Reissued by PMLR on 09 October 2024.

Related Material