Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models

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.

Cite

Text

Heskes et al. "Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models." Neural Information Processing Systems, 2020.

Markdown

[Heskes et al. "Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/heskes2020neurips-causal/)

BibTeX

@inproceedings{heskes2020neurips-causal,
  title     = {{Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models}},
  author    = {Heskes, Tom and Sijben, Evi and Bucur, Ioan Gabriel and Claassen, Tom},
  booktitle = {Neural Information Processing Systems},
  year      = {2020},
  url       = {https://mlanthology.org/neurips/2020/heskes2020neurips-causal/}
}