Rational Shapley Values

TL;DR

Rational Shapley values is a new XAI method that combines feature attribution and counterfactual explanations using decision theory and causal modeling, improving interpretability of complex models.

Contribution

Introduces rational Shapley values, a flexible XAI approach that incorporates user goals and knowledge, addressing limitations of existing methods.

Findings

Outperforms state-of-the-art XAI tools in experiments

Provides a formal framework integrating decision theory and causal modeling

Enhances interpretability for high-stakes decision models

Abstract

Explaining the predictions of opaque machine learning algorithms is an important and challenging task, especially as complex models are increasingly used to assist in high-stakes decisions such as those arising in healthcare and finance. Most popular tools for post-hoc explainable artificial intelligence (XAI) are either insensitive to context (e.g., feature attributions) or difficult to summarize (e.g., counterfactuals). In this paper, I introduce $\textit{rational Shapley values}$, a novel XAI method that synthesizes and extends these seemingly incompatible approaches in a rigorous, flexible manner. I leverage tools from decision theory and causal modeling to formalize and implement a pragmatic approach that resolves a number of known challenges in XAI. By pairing the distribution of random variables with the appropriate reference class for a given explanation task, I illustrate through theory and experiments how user goals and knowledge can inform and constrain the solution set in an iterative fashion. The method compares favorably to state of the art XAI tools in a range of quantitative and qualitative comparisons.