Abstract
Multi-Criteria Decision Aiding arises in many industrial applications where the user needs an explanation of the recommendation. We consider in particular an explanation taking the form of a contribution level assigned to each variable. Decision models are often hierarchical, and the influence is computed by the Winter value, which is an extension of the Shapley value on trees. The contribution of the paper is to propose an exact algorithm to compute efficiently the Winter values for a very general class of decision models known as the Choquet integral. The main idea of our algorithm is to prune the combinatorial structure on which the Winter value is computed, based on upper and lower bounds of the utility on subtrees. Extensive simulations show that this new algorithm provides very significant computation gains compared to the state of the art.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arrieta, A.B., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115 (2020)
Belahcène, K., Labreuche, C., Maudet, N., Mousseau, V., Ouerdane, W.: Comparing options with argument schemes powered by cancellation. In: Proceedings of the Twenty-Eight International Joint Conference on Artificial Intelligence (IJCAI 2019), Macao, China, pp. 1537–1543, August 2019
Bresson, R., Cohen, J., Hüllermeier, E., Labreuche, C., Sebag, M.: Neural representation and learning of hierarchical 2-additive Choquet integrals. In: Proceedings of the Twenty-Eight International Joint Conference on Artificial Intelligence (IJCAI 2020), Yokohoma, Japan, pp. 1984–1991 (2020)
Carenini, G., Moore, J.D.: Generating and evaluating evaluative arguments. Artif. Intell. 170, 925–952 (2006)
Castro, J., Gómez, D., Tejada, J.: Polynomial calculation of the Shapley value based on sampling. Comput. Oper. Res. 36, 1726–1730 (2009)
Chen, J., Song, L., Wainwright, M., Jordan, M.: L-Shapley and C-Shapley: efficient model interpretation for structured data. arXiv preprint arXiv:1808.02610 (2018)
Choquet, G.: Theory of capacities. Annales de l’Institut Fourier 5, 131–295 (1953)
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, USA, May 2016
Figueira, J., Greco, S., Ehrgott, M., (eds.) Multiple Criteria Decision Analysis: State of the Art Surveys, 2nd edition. Kluwer Acad. Publ. (2016)
Galand, L., Lesca, J., Perny, P.: Dominance rules for the Choquet integral in multiobjective dynamic programming. In: 23rd International Joint Conference on Artificial Intelligence (IJCAI 2013), Beijing, China, pp. 538–544, August 2013
Grabisch, M., Kojadinovic, I., Meyer, P.: A review of capacity identification methods for Choquet integral based multi-attribute utility theory – applications of the Kappalab R package. Eur. J. Oper. Res. 186, 766–785 (2008)
Grabisch, M., Labreuche, C.: A decade of application of the Choquet and Sugeno integrals in multi-criteria decision aid. Ann. Oper. Res. 175, 247–286 (2010)
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. 51(6), 1–42 (2018)
Herlocker, J.L., Konstan, J.A., Riedl, J.: Explaining collaborative filtering recommendations. In: CSCW, pp. 241–250 (2000)
Klein, D.A.: Decision Analytic Intelligent Systems: Automated Explanation and Knowledge Acquisition. Lawrence Erlbaum Associates (1994)
Labreuche, C., Fossier, S.: Explaining multi-criteria decision aiding models with an extended shapley value. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI 2018), Stockholm, Sweden, pp. 331–339, July 2018
Labreuche, C.: A general framework for explaining the results of a multi-attribute preference model. Artif. Intell. 175, 1410–1448 (2011)
Labreuche, C.: Explaining hierarchical multi-linear models. In: Proceedings of the 13th International Conference on Scalable Uncertainty Management (SUM 2019), Compiègne, France, December 2019
Lundberg, S., Lee, S.I.: A unified approach to interpreting model predictions. In: Guyon, I., et al. (eds.) 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, pp. 4768–4777 (2017)
Lundberg, S., Enrion, G., Lee, S.I.: Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888 (2018)
Maleki, S., Tran-Thanh, L., Hines, G., Rahwan, T., Rogers, A.: Bounding the estimation error of sampling-based Shapley value approximation. arXiv:1306.4265 (2013)
Merrick, L., Taly, A.: The explanation game: explaining machine learning models with cooperative game theory. arXiv preprint arXiv:1909.08128 (2018)
Ovchinnikov, S.: Max-min representation of piecewise linear functions. Contrib. Algebra Geom. 43, 297–327 (2002)
Owen, A.B.: Sobol’ indices and Shapley value. SIAM/ASA J. Uncertain. Quant. 2, 245–251 (2014)
Owen, G.: Values of games with a priori unions. In: Moeschlin, O., Hein, R., (ed.), Essays in Mathematical Economics and Game Theory, pp. 76–88. Springer, Heidelberg (1977). https://doi.org/10.1007/978-3-642-45494-3_7
Ribeiro, M.T., 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, San Francisco, California, USA, pp. 1135–1144 (2016)
Saltelli, A., et al.: Global Sensitivity Analysis: The Primer. Wiley, New York (2008)
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, number 28 in Annals of Mathematics Studies, pp. 307–317. Princeton University Press (1953)
Štrumbelj, E., Kononenko, I.: An efficient explanation of individual classifications using game theory. J. Mach. Learn. Res. 11, 1–18 (2010)
Winter, E.: A value for cooperative games with levels structure of cooperation. Int. J. Game Theory 18, 227–240 (1989)
Zhong, Q., Fan, X., Toni, F., Luo, X.: Explaining best decisions via argumentation. In: Proceedings of the European Conference on Social Intelligence (ECSI-2014), Barcelona, Spain, pp. 224–237, November 2014
Acknowledgments
This paper is supported by the European Union’s Horizon 2020 research and innovation programme under grant agreement No 825619. AI4EU Project.(\(^2\) https://www.ai4europe.eu/).
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
Labreuche, C. (2021). Explanation with the Winter Value: Efficient Computation for Hierarchical Choquet Integrals. 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_34
Download citation
DOI: https://doi.org/10.1007/978-3-030-86772-0_34
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)