Log In Sign Up

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

by   Tom Heskes, et al.

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. In this paper, we propose a novel framework for computing Shapley values that generalizes recent work that aims to circumvent the independence assumption. By employing Pearl's do-calculus, we show how these 'causal' Shapley values can be derived for general causal graphs without sacrificing any of their desirable properties. Moreover, causal Shapley values enable us to separate the contribution of direct and indirect effects. We provide a practical implementation for computing causal Shapley values based on causal chain graphs when only partial information is available and illustrate their utility on a real-world example.


page 1

page 2

page 3

page 4


Problems with Shapley-value-based explanations as feature importance measures

Game-theoretic formulations of feature importance have become popular as...

Socioeconomic disparities and COVID-19: the causal connections

The analysis of causation is a challenging task that can be approached i...

Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability

Explaining AI systems is fundamental both to the development of high per...

Insights into the "cross-world" independence assumption of causal mediation analysis

Causal mediation analysis is a useful tool for epidemiological research,...

Rational Shapley Values

Explaining the predictions of opaque machine learning algorithms is an i...