Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression

Ian Covert, Su-In Lee
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:3457-3465, 2021.

Abstract

The Shapley value concept from cooperative game theory has become a popular technique for interpreting ML models, but efficiently estimating these values remains challenging, particularly in the model-agnostic setting. Here, we revisit the idea of estimating Shapley values via linear regression to understand and improve upon this approach. By analyzing the original KernelSHAP alongside a newly proposed unbiased version, we develop techniques to detect its convergence and calculate uncertainty estimates. We also find that the original version incurs a negligible increase in bias in exchange for significantly lower variance, and we propose a variance reduction technique that further accelerates the convergence of both estimators. Finally, we develop a version of KernelSHAP for stochastic cooperative games that yields fast new estimators for two global explanation methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v130-covert21a, title = { Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression }, author = {Covert, Ian and Lee, Su-In}, booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, pages = {3457--3465}, year = {2021}, editor = {Banerjee, Arindam and Fukumizu, Kenji}, volume = {130}, series = {Proceedings of Machine Learning Research}, month = {13--15 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v130/covert21a/covert21a.pdf}, url = {https://proceedings.mlr.press/v130/covert21a.html}, abstract = { The Shapley value concept from cooperative game theory has become a popular technique for interpreting ML models, but efficiently estimating these values remains challenging, particularly in the model-agnostic setting. Here, we revisit the idea of estimating Shapley values via linear regression to understand and improve upon this approach. By analyzing the original KernelSHAP alongside a newly proposed unbiased version, we develop techniques to detect its convergence and calculate uncertainty estimates. We also find that the original version incurs a negligible increase in bias in exchange for significantly lower variance, and we propose a variance reduction technique that further accelerates the convergence of both estimators. Finally, we develop a version of KernelSHAP for stochastic cooperative games that yields fast new estimators for two global explanation methods. } }
Endnote
%0 Conference Paper %T Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression %A Ian Covert %A Su-In Lee %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-covert21a %I PMLR %P 3457--3465 %U https://proceedings.mlr.press/v130/covert21a.html %V 130 %X The Shapley value concept from cooperative game theory has become a popular technique for interpreting ML models, but efficiently estimating these values remains challenging, particularly in the model-agnostic setting. Here, we revisit the idea of estimating Shapley values via linear regression to understand and improve upon this approach. By analyzing the original KernelSHAP alongside a newly proposed unbiased version, we develop techniques to detect its convergence and calculate uncertainty estimates. We also find that the original version incurs a negligible increase in bias in exchange for significantly lower variance, and we propose a variance reduction technique that further accelerates the convergence of both estimators. Finally, we develop a version of KernelSHAP for stochastic cooperative games that yields fast new estimators for two global explanation methods.
APA
Covert, I. & Lee, S.. (2021). Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression . Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 130:3457-3465 Available from https://proceedings.mlr.press/v130/covert21a.html.

Related Material