Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models
Tom Heskes, Evi Sijben, Ioan Gabriel Bucur, Tom Claassen
Abstract
Shapley values underlie one of the most popular model-agnostic methods within explainable artificial intelligence. These values are designed to attribute the difference between a model's prediction and an average baseline to the different features used as input to the model. Being based on solid game-theoretic principles, Shapley values uniquely satisfy several desirable properties, which is why they are increasingly used to explain the predictions of possibly complex and highly non-linear machine learning models. Shapley values are well calibrated to a user’s intuition when features are independent, but may lead to undesirable, counterintuitive explanations when the independence assumption is violated.
BibTeX
@inproceedings{NEURIPS2020_32e54441,
author = {Heskes, Tom and Sijben, Evi and Bucur, Ioan Gabriel and Claassen, Tom},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {4778--4789},
publisher = {Curran Associates, Inc.},
title = {Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/32e54441e6382a7fbacbbbaf3c450059-Paper.pdf},
volume = {33},
year = {2020}
}