Abstract
Explanation in Artificial Intelligence is often focused on providing reasons for why a model under consideration and its outcome are correct. Recently, research in explainable machine learning has initiated a shift in focus on including so-called counterfactual explanations. In this paper we propose to combine both types of explanation in the context of explaining Bayesian networks. To this end we introduce persuasive contrastive explanations that aim to provide an answer to the question Why outcome t instead of \(t^\prime ?\) posed by a user. In addition, we propose an algorithm for computing persuasive contrastive explanations. Both our definition of persuasive contrastive explanation and the proposed algorithm can be employed beyond the current scope of Bayesian networks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Change history
19 September 2021
In the originally published article, the pseudocode in Algorithm 1 does not include the lines that were left intentionally blank. This has been corrected to include 2 lines (line 9 and 14), which are intentionally left blank in the algorithm for the addition of new code to these lines.
Notes
- 1.
In case \(\top {(T\!\mid \!\mathbf {e})}\) is not unique, we assume all modes are output to the user and that \(t^\prime \) is not among these.
- 2.
All mentioned networks are available from https://www.bnlearn.com/bnrepository/.
References
Albini, E., Rago, A., Baroni, P., Toni, F.: Relation-based counterfactual explanations for Bayesian network classifiers. In: Bessiere, C. (ed.) Proceedings of the 29th International Joint Conference on Artificial Intelligence, pp. 451–457 (2020)
Baker, M., Boult, T.E.: Pruning Bayesian networks for efficient computation. In: Bonissone, P., Henrion, M., Kanal, L., Lemmer, J. (eds.) Uncertainty in Artificial Intelligence 6. Elsevier Science, Amsterdam (1991)
Cooper, G.F.: The computational complexity of probabilistic inference using Bayesian belief networks. Artif. Intell. 42, 393–405 (1990)
Darwiche, A., Hirth, A.: On the reasons behind decisions. In: De Giacomo, G., Catala, A., Dilkina, B., Milano, M., Barro, S., BugarÃn, A., Lang, J. (eds.) Proceedings of 24th European Conference on Artificial Intelligence, pp. 712–720. IOS Press (2020)
Derks, I.P., de Waal, A.: A taxonomy of explainable Bayesian networks. In: Gerber, A. (ed.) Artificial Intelligence Research, pp. 220–235. Springer, Cham (2020)
van der Gaag, L.C., Bodlaender, H.L., Feelders, A.: Monotonicity in Bayesian networks. In: Chickering, M., Halpern, J. (eds.) Proceedings of the 20th Conference on Uncertainty in Artificial Intelligence, pp. 569–576 (2004)
Ignatiev, A., Narodytska, N., Asher, N., Marques-Silva, J.: From contrastive to abductive explanations and back again. In: Baldoni, M., Bandini, S. (eds.) AIxIA 2020. LNCS (LNAI), vol. 12414, pp. 335–355. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-77091-4_21
Jensen, F.V., Nielsen, T.D.: Bayesian networks and decision graphs. Springer Science & Business Media, 2 edn. (2007)
Koopman, T.: Computing Contrastive, Counterfactual Explanations for Bayesian Networks. Master’s thesis, Universiteit Utrecht, The Netherlands (2020). https://dspace.library.uu.nl/handle/1874/398728
Kyrimi, E., Marsh, W.: A progressive explanation of inference in ‘hybrid’ Bayesian networks for supporting clinical decision making. In: Antonucci, A., Corani, G., de Campos, C.P. (eds.) Proceedings of the 8th Conference on Probabilistic Graphical Models, pp. 275–286 (2016)
Lacave, C., DÃez, F.J.: A review of explanation methods for Bayesian networks. Knowl. Eng. Rev. 17(2), 107–127 (2002)
van Leersum, J.: Explaining the reasoning of Bayesian networks with intermediate nodes and clusters. Master’s thesis, Utrecht University (2015). http://dspace.library.uu.nl/handle/1874/313520
Marques-Silva, J., Gerspacher, T., Cooper, M., Ignatiev, A., Narodytska, N.: Explaining naive Bayes and other linear classifiers with polynomial time and delay. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 20590–20600. Curran Associates, Inc. (2020)
Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2019)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann Publishers (1988)
Shih, A., Choi, A., Darwiche, A.: A symbolic approach to explaining Bayesian network classifiers. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 5103–5111 (2018)
Shih, A., Choi, A., Darwiche, A.: Compiling Bayesian network classifiers into decision graphs. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence, pp. 7966–7974 (2019)
Spiegelhalter, D.J., Dawid, A.P., Lauritzen, S.L., G.Cowell, R.: Bayesian analysis in expert systems. Stat. Sci. 8(3), 219–247 (1993)
Suermondt, H.J.: Explanation in Bayesian belief networks. Ph.D. thesis, Stanford University (1992)
Timmer, S.T., Meyer, J.-J.C., Prakken, H., Renooij, S., Verheij, B.: Explaining Bayesian networks using argumentation. In: Destercke, S., Denoeux, T. (eds.) ECSQARU 2015. LNCS (LNAI), vol. 9161, pp. 83–92. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-20807-7_8
Verma, S., Dickerson, J.P., Hines, K.E.: Counterfactual explanations for machine learning: A review. ArXiv abs/2010.10596 (2020)
Vlek, C., Prakken, H., Renooij, S., Verheij, B.: A method for explaining Bayesian networks for legal evidence with scenarios. Artif. Intell. Law 24(3), 285–324 (2016)
van der Waa, J., Robeer, M., van Diggelen, J., Brinkhuis, M., Neerincx, M.: Contrastive explanations with local foil trees. In: Proceedings of the Workshop on Human Interpretability in Machine Learning, pp. 41–47 (2018)
Wachter, S., Mittelstadt, B., Russell, C.: Counterfactual explanations without opening the black box: automated decisions and the GPDR. Harvard J. Law Technol. 31, 841 (2017)
Yap, G.E., Tan, A.H., Pang, H.H.: Explaining inferences in Bayesian networks. Appl. Intell. 29(3), 263–278 (2008)
Acknowledgements
This research was partially funded by the Hybrid Intelligence Center, a 10-year programme funded by the Dutch Ministry of Education, Culture and Science through the Netherlands Organisation for Scientific Research, https://hybrid-intelligence-centre.nl. We would like to thank the anonymous reviewers for their useful and inspiring comments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Koopman, T., Renooij, S. (2021). Persuasive Contrastive Explanations for Bayesian Networks. In: Vejnarová, J., Wilson, N. (eds) Symbolic and Quantitative Approaches to Reasoning with Uncertainty. ECSQARU 2021. Lecture Notes in Computer Science(), vol 12897. Springer, Cham. https://doi.org/10.1007/978-3-030-86772-0_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-86772-0_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86771-3
Online ISBN: 978-3-030-86772-0
eBook Packages: Computer ScienceComputer Science (R0)