Abstract
This work introduces the notion of intermediate concepts based on levels structure to aid explainability for black-box models. The levels structure is a hierarchical structure in which each level corresponds to features of a dataset (i.e., a player-set partition). The level of coarseness increases from the trivial set, which only comprises singletons, to the set, which only contains the grand coalition. In addition, it is possible to establish meronomies, i.e., part-whole relationships, via a domain expert that can be utilised to generate explanations at an abstract level. We illustrate the usability of this approach in a real-world car model example and the Titanic dataset, where intermediate concepts aid in explainability at different levels of abstraction.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aumann, R.J., Dreze, J.H.: Cooperative games with coalition structures. Int. J. Game Theory 3(4), 217–237 (1974)
Aumarm, R.J.: Acceptable points in general cooperative N-person games. Contrib. Theory Games (AM-40) 4, 287 (2016)
Biecek, P., Burzykowski, T.: Explanatory Model Analysis. Chapman and Hall/CRC, New York (2021)
Bohanec, M., Rajkovič, V.: Knowledge acquisition and explanation for multi-attribute decision. In: 8th International Workshop on Expert Systems and Their Applications, Avignon, France, pp. 59–78 (1988)
Faigle, U., Kern, W.: The shapley value for cooperative games under precedence constraints. Int. J. Game Theory 21(3), 249–266 (1992)
Främling, K.: Explaining results of neural networks by contextual importance and utility. In: Andrews, R., Diederich, J. (eds.) Rules and Networks: Proceedings of the Rule Extraction from Trained Artificial Neural Networks Workshop, AISB 1996 Conference, Brighton, UK (1996)
Främling, K.: Modélisation et apprentissage des préférences par réseaux de neurones pour l’aide à la décision multicritère. Ph.D. thesis, INSA de Lyon (1996)
Främling, K.: Decision theory meets explainable AI. In: Calvaresi, D., Najjar, A., Winikoff, M., Främling, K. (eds.) EXTRAAMAS 2020. LNCS (LNAI), vol. 12175, pp. 57–74. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-51924-7_4
Främling, K.: Contextual importance and utility: a theoretical foundation. In: Long, G., Yu, X., Wang, S. (eds.) AI 2022. LNCS (LNAI and LNB), vol. 13151, pp. 117–128. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-97546-3_10
Främling, K., Graillot, D.: Extracting explanations from neural networks. In: ICANN 1995 Conference, Paris, France (1995)
Harsanyi, J.C.: A simplified bargaining model for the n-person cooperative game. In: Harsanyi, J.C. (ed.) Papers in Game Theory. Theory and Decision Library, vol. 28, pp. 44–70. Springer, Dordrecht (1982). https://doi.org/10.1007/978-94-017-2527-9_3
Hart, S., Mas-Colell, A.: Bargaining and value. Econom.: J. Econom. Soc. 357–380 (1996)
Jullum, M., Redelmeier, A., Aas, K.: GroupShapley: efficient prediction explanation with shapley values for feature groups (2021). https://doi.org/10.48550/ARXIV.2106.12228, https://arxiv.org/abs/2106.12228
Patil, M.S.: Explainability in autonomous pedagogically structured scenarios (2022). arXiv:2210.12140, https://arxiv.org/pdf/2210.12140.pdf
Patil, M.S.: Towards preserving semantic structure in argumentative multi-agent via abstract interpretations (2022). arXiv:2211.15782, https://arxiv.org/pdf/2211.15782.pdf
Patil, M.S.: Modelling control arguments via cooperation logic in unforeseen scenarios (2022). arXiv:2210.12114, https://arxiv.org/pdf/2210.12114.pdf
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 4765–4774. Curran Associates, Inc. (2017)
Myerson, R.B.: Conference structures and fair allocation rules. Int. J. Game Theory 9(3), 169–182 (1980)
van den Nouweland, A., Borm, P., Tijs, S.: Allocation rules for hypergraph communication situations. Int. J. Game Theory 20(3), 255–268 (1992)
Owen, G.: Values of games with a priori unions. In: Henn, R., Moeschlin, O. (eds.) Mathematical Economics and Game Theory. Lecture Notes in Economics and Mathematical Systems, vol. 141, pp. 76–88. Springer, Heidelberg (1977). https://doi.org/10.1007/978-3-642-45494-3_7
Shapley, L.S.: A value for n-person games. In: Kuhn, H.W., Tucker, A.W. (eds.) Contributions to the Theory of Games II, pp. 307–317. Princeton University Press, Princeton (1953)
Štrumbelj, E., Kononenko, I.: Explaining prediction models and individual predictions with feature contributions. Knowl. Inf. Syst. 41(3), 647–665 (2014)
Winter, E.: A value for cooperative games with levels structure of cooperation. Int. J. Game Theory 18(2), 227–240 (1989)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Patil, M.S., Främling, K. (2023). Do Intermediate Feature Coalitions Aid Explainability of Black-Box Models?. In: Longo, L. (eds) Explainable Artificial Intelligence. xAI 2023. Communications in Computer and Information Science, vol 1901. Springer, Cham. https://doi.org/10.1007/978-3-031-44064-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-44064-9_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44063-2
Online ISBN: 978-3-031-44064-9
eBook Packages: Computer ScienceComputer Science (R0)