Abstract
We propose a novel symbolic approach to provide counterfactual explanations for a classifier predictions. Contrary to most explanation approaches where the goal is to understand which and to what extent parts of the data helped to give a prediction, counterfactual explanations indicate which features must be changed in the data in order to change this classifier prediction. Our approach is symbolic in the sense that it is based on encoding the decision function of a classifier in an equivalent CNF formula. In this approach, counterfactual explanations are seen as the Minimal Correction Subsets (MCS), a well-known concept in knowledge base reparation. Hence, this approach takes advantage of the strengths of already existing and proven solutions for the generation of MCS. Our preliminary experimental studies on Bayesian classifiers show the potential of this approach on several datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A unit clause involves only one Boolean variable represented by a literal.
- 2.
Available at http://www.cril.univ-artois.fr/enumcs/.
References
Biere, A., Heule, M., van Maaren, H.: Handbook of Satisfiability, vol. 185. IOS Press (2009)
Cabodi, G., Nocco, S., Quer, S.: Improving SAT-based bounded model checking by means of BDD-based approximate traversals. In: 2003 Design, Automation and Test in Europe Conference and Exhibition, pp. 898–903. IEEE (2003)
Grégoire, É., Izza, Y., Lagniez, J.M.: Boosting MCSes enumeration. In: IJCAI, pp. 1309–1315 (2018)
Shi, W., Shih, A., Darwiche, A., Choi, A.: On tractable representations of binary neural networks. arXiv preprint arXiv:2004.02082 (2020)
Shih, A., Choi, A., Darwiche, A.: A symbolic approach to explaining Bayesian network classifiers. arXiv preprint arXiv:1805.03364 (2018)
Shih, A., Choi, A., Darwiche, A.: Compiling Bayesian network classifiers into decision graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 7966–7974 (2019)
Acknowledgment
This work is done as part of a PhD thesis benefiting from the support of the Région Hauts-de-France.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Boumazouza, R., Cheikh-Alili, F., Mazure, B., Tabia, K. (2020). A Symbolic Approach for Counterfactual Explanations. In: Davis, J., Tabia, K. (eds) Scalable Uncertainty Management. SUM 2020. Lecture Notes in Computer Science(), vol 12322. Springer, Cham. https://doi.org/10.1007/978-3-030-58449-8_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-58449-8_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58448-1
Online ISBN: 978-3-030-58449-8
eBook Packages: Computer ScienceComputer Science (R0)