Abstract
This paper provides new theory to support to the eXplainable AI (XAI) method Contextual Importance and Utility (CIU). CIU arithmetic is based on the concepts of Multi-Attribute Utility Theory, which gives CIU a solid theoretical foundation. The novel concept of contextual influence is also defined, which makes it possible to compare CIU directly with so-called additive feature attribution (AFA) methods for model-agnostic outcome explanation. One key takeaway is that the ‘influence’ concept used by AFA methods is inadequate for outcome explanation purposes even for simple models to explain. Experiments with simple models show that explanations using contextual importance (CI) and contextual utility (CU) produce explanations where influence-based methods fail. It is also shown that CI and CU guarantees explanation faithfulness towards the explained model.
The work is partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Called baseline by many authors but ‘baseline’ seems to be used also for other purposes. This is why we prefer using ‘reference level’.
References
Dyer, J.S.: Maut — multiattribute utility theory. In: Multiple Criteria Decision Analysis: State of the Art Surveys. ISORMS, vol. 78, pp. 265–292. Springer, New York (2005). https://doi.org/10.1007/0-387-23081-5_7
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, 1–2 April 1996
Främling, K.: Modélisation et apprentissage des préférences par réseaux de neurones pour l’aide à la décision multicritère. Phd thesis, INSA de Lyon, March 1996
Främling, K.: Contextual importance and utility in R: the ‘ciu’ package. In: Proceedings of 1st Workshop on Explainable Agency in Artificial Intelligence, at 35th AAAI Conference on Artificial Intelligence, 2–9 February 2021, pp. 110–114 (2021)
Främling, K., Knapic̆, S., Malhi, A.: ciu.image: an R package for explaining image classification with contextual importance and utility. In: Calvaresi, D., Najjar, A., Winikoff, M., Främling, K. (eds.) EXTRAAMAS 2021. LNCS (LNAI), vol. 12688, pp. 55–62. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-82017-6_4
Främling, K., Westberg, M., Jullum, M., Madhikermi, M., Malhi, A.: Comparison of contextual importance and utility with lime and Shapley values. In: Calvaresi, D., Najjar, A., Winikoff, M., Främling, K. (eds.) Explainable and Transparent AI and Multi-Agent Systems - 3rd International Workshop, EXTRAAMAS 2021, pp. 39–54. Lecture Notes in Computer Science, Springer, Germany (2021)
Knapič, S., Malhi, A., Saluja, R., Främling, K.: Explainable artificial intelligence for human decision support system in the medical domain. Mach. Learn. Knowl. Extr. 3(3), 740–770 (2021)
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)
Molnar, C., Casalicchio, G., Bischl, B.: iml: an R package for interpretable machine learning. J. Open Source Softw. 3(26), 786 (2018)
von Neumann, J., Morgenstern, O.: Theory of Games and Economic Behavior. Princeton University Press (1947)
Pedersen, T.L., Benesty, M.: lime: local interpretable model-agnostic explanations (2019). https://CRAN.R-project.org/package=lime. r package version 0.5.1
Ribeiro, M.T., Singh, S., Guestrin, C.: “ why should i trust you?” Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016)
Shapley, L.: A value for n-person games. In: Kuhn, H., Tucker, A. (eds.) Contributions to the Theory of Games, vol. II, Annals of Mathematics Studies, vol. 28, pp. 307–317. Princeton University Press, Princeton (1953)
Štrumbelj, E., Kononenko, I.: An efficient explanation of individual classifications using game theory. J. Mach. Learn. Res. 11, 1–18 (2010)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Främling, K. (2022). Contextual Importance and Utility: A Theoretical Foundation. In: Long, G., Yu, X., Wang, S. (eds) AI 2021: Advances in Artificial Intelligence. AI 2022. Lecture Notes in Computer Science(), vol 13151. Springer, Cham. https://doi.org/10.1007/978-3-030-97546-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-97546-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-97545-6
Online ISBN: 978-3-030-97546-3
eBook Packages: Computer ScienceComputer Science (R0)