Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models
This addresses a key limitation in explainable AI for users of complex models by improving interpretability when feature independence is violated, though it builds incrementally on prior work to circumvent the independence assumption.
The paper tackles the problem of Shapley values producing counterintuitive explanations when features are dependent, by proposing a novel framework that uses Pearl's do-calculus to compute causal Shapley values for general causal graphs, enabling separation of direct and indirect effects and providing a practical implementation for real-world use.
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.