Abstract
When used in the context of decision theory, feature importance expresses how much changing the value of a feature can change the model outcome (or the utility of the outcome), compared to other features. Feature importance should not be confused with the feature influence used by most state-of-the-art post-hoc Explainable AI methods. Contrary to feature importance, feature influence is measured against a reference level or baseline. The Contextual Importance and Utility (CIU) method provides a unified definition of global and local feature importance that is applicable also for post-hoc explanations, where the value utility concept provides instance-level assessment of how favorable or not a feature value is for the outcome. The paper shows how CIU can be applied to both global and local explainability, assesses the fidelity and stability of different methods, and shows how explanations that use contextual importance and contextual utility can provide more expressive and flexible explanations than when using influence only.
The work is partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation.
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
Notes
- 1.
Intermediate concepts also deal with dependencies between features. However, in this paper we assume that the features are independent, as is the case for Shapley value and LIME too.
- 2.
The approach in [10] is applicable to any feature set \(\{i\}\) and \(\{I\}\), including \(1,\dots ,N\).
References
Andrews, R., Diederich, J., Tickle, A.B.: Survey and critique of techniques for extracting rules from trained artificial neural networks. Know. Based Syst. 8(6), 373–389 (1995)
Biecek, P., Burzykowski, T.: Explanatory Model Analysis. Chapman and Hall/CRC, New York (2021)
Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)
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
Fishburn, P.C.: Utility Theory and Decision Theory, pp. 303–312. Palgrave Macmillan, London (1990)
Fisher, A., Rudin, C., Dominici, F.: All models are wrong, but many are useful: learning a variable’s importance by studying an entire class of prediction models simultaneously. J. Mach. Learn. Res. 20(177), 1–81 (2019)
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. Phd 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, 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 in R: the ‘ciu’ package. In: Proceedings of \(1^{st}\) Workshop on Explainable Agency in Artificial Intelligence, at \(35^{th}\) AAAI Conference on Artificial Intelligence, 2–9 February 2021, pp. 110–114 (2021)
Keeney, R.L., Raiffa, H.: Decisions with Multiple Objectives: Preferences and Value Trade-Offs. Cambridge University Press, Cambridge (1993)
Kuhn, M.: Building predictive models in R using the caret package. J. Stat. Softw. Art. 28(5), 1–26 (2008)
Kumar, I.E., Venkatasubramanian, S., Scheidegger, C., Friedler, S.: Problems with shapley-value-based explanations as feature importance measures. In: International Conference on Machine Learning, pp. 5491–5500. PMLR (2020)
Lundberg, S.M., Erion, G.G., Lee, S.I.: Consistent individualized feature attribution for tree ensembles. CoRR abs/1802.03888 (2018)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (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)
Pedersen, T.L., Benesty, M.: lime: Local Interpretable Model-Agnostic Explanations (2019). 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.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)
Shortliffe, E.H., Davis, R., Axline, S.G., Buchanan, B.G., Green, C., Cohen, S.N.: Computer-based consultations in clinical therapeutics: explanation and rule acquisition capabilities of the MYCIN system. Comput. Biomed. Res. 8(4), 303–320 (1975)
Štrumbelj, E., Kononenko, I.: Explaining prediction models and individual predictions with feature contributions. Knowl. Inf. Syst. 41(3), 647–665 (2014)
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
Främling, K. (2023). Feature Importance versus Feature Influence and What It Signifies for Explainable AI. 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_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-44064-9_14
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)