Abstract
Explanation methods can be formal or heuristic-based. Many explanation methods have been developed. Formal methods provide principles to derive sufficient reasons (prime implicants) or necessary reasons (counterfactuals, causes). These approaches are appealing but require to discretize the input and output spaces. Heuristic-based approaches such as feature attribution (such as the Shapley value) work in any condition but the relation to explanation is less clear. We show that they cannot distinguish between conjunction and disjunction, which is not the case with sufficient explanations. This work is an initial work that aims at combining some idea of prime implicants into feature attribution, in order to measure sufficiency of the features. We apply it to two values - the proportional division and the Shapley value.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Aas, K., Jullum, M., Løland, A.: Explaining individual predictions when features are dependent: more accurate approximations to Shapley values. In: arXiv preprint arXiv:1903.10464 (2019)
Arrieta, A.B., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115 (2020)
Audemard, G., Koriche, F., Marquis, P.: On tractable XAI queries based on compiled representations. In: Proceedings of the 17th International Conference on Principles of Knowledge Representation and Reasoning (KR 2020), pp. 838–849. Rhodes, Greece (2020)
Banzhaf, J.: Weighted voting doesn’t work: a mathematical analysis. Rutgers Law Rev. 19, 317–343 (1965)
Bisdorff, R., Dias, L.C., Meyer, P., Mousseau, V., Pirlot, M. (eds.): Evaluation and Decision Models with Multiple Criteria. IHIS, Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-46816-6
Cano, J.R., Gutiérrez, P., Krawczyk, B., Woźniak, M., García, S.: Monotonic classification: an overview on algorithms, performance measures and data sets. arXiv:1811.07155 (2018)
Darwiche, A., Hirth, A.: On the reasons behind decisions. In: Proceedings of the European Conference on Artificial Intelligence (ECAI 2020), pp. 712–720. Santiago, Spain (2020)
Datta, A., Sen, S., Zick, Y.: Algorithmic transparency via quantitative input influence: theory and experiments with learning systems. In: IEEE Symposium on Security and Privacy. San Jose, CA (2016)
Halpern, J.Y., Pearl, J.: Causes and explanations: a structural-model approach - Part I: causes. In: Proceedings of the Seventeenth Conference on Uncertainy in Artificial Intelligence (UAI), pp. 194–202. San Francisco, CA (2001)
Halpern, J.Y., Pearl, J.: Causes and explanations: a structural-model approach - Part II: explanations. Br. J. Philos. Sci. 56(4), 889–911 (2005)
Ignatiev, A., Narodytska, N., Marques-Silva, J.: Abduction-based explanations for machine learning models. In: AAAI, pp. 1511–1519. Honolulu, Hawai (2019)
Kumar, I., Venkatasubramanian, S., Scheidegger, C., Friedler, S.: Problems with Shapley-value-based explanations as feature importance measures. In: 37th International Conference on Machine Learning (ICML 2020), pp. 5491–5500 (2020)
Lemaire, J.: An application of game theory: cost allocation. ASTIN Bull.: J. IAA 14, 61–81 (1984)
Lundberg, S., Enrion, G., Lee, S.: Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888 (2018)
Lundberg, S., Lee, S.: A unified approach to interpreting model predictions. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) 31st Conference on Neural Information Processing Systems (NIPS 2017), pp. 4768–4777. Long Beach, CA (2017)
Marquis, P.: Consequence finding algorithms. In: Handbook of Defeasible Reasoning and Uncertainty Management Systems, pp. 41–145 (2000)
Merrick, L., Taly, A.: The explanation game: explaining machine learning models with cooperative game theory. arXiv preprint arXiv:1909.08128 (2018)
Mothilal, R.K., Mahajan, D., Tan, C., Sharma, A.: Towards unifying feature attribution and counterfactual explanations: different means to the same end. In: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society (AIES 2021), pp. 652–663 (2021)
Ribeiro, M., Singh, S., Guestrin, C.: Why should i trust you?: explaining the predictions of any classifier. In: KDD 2016 Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144. San Francisco, California (2016)
Schmeidler, D.: The nucleolus of a characteristic function game. SIAM J. Appl. Math. 17(6), 1163–1170 (1969)
Shapley, L.S.: A value for \(n\)-person games. In: Kuhn, H.W., Tucker, A.W. (eds.) Contributions to the Theory of Games, Vol. II, pp. 307–317, no. 28 in Annals of Mathematics Studies, Princeton University Press (1953)
Shih, A., Choi, A., Darwiche, A.: A symbolic approach to explaining Bayesian network classifiers. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI 2018), pp. 5103–5111. Stockholm, Sweden (2018)
Verma, S., Dickerson, J., Hines, K.: Counterfactual explanations for machine learning: a review. arXiv preprint arxiv:2010.10596 (2020)
Štrumbelj, E., Kononenko, I.: An efficient explanation of individual classifications using game theory. J. Mach. Learn. Res. 11, 1–18 (2010)
Zou, Z., van den Brink, R., Chun, Y., Funaki, Y.: Axiomatizations of the proportional division value. Soc. Choice Welfare 57, 35–62 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Labreuche, C. (2022). Explanation of Pseudo-Boolean Functions Using Cooperative Game Theory and Prime Implicants. In: Dupin de Saint-Cyr, F., Öztürk-Escoffier, M., Potyka, N. (eds) Scalable Uncertainty Management. SUM 2022. Lecture Notes in Computer Science(), vol 13562. Springer, Cham. https://doi.org/10.1007/978-3-031-18843-5_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-18843-5_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18842-8
Online ISBN: 978-3-031-18843-5
eBook Packages: Computer ScienceComputer Science (R0)