Model Explanations via the Axiomatic Causal Lens
This work addresses the need for trustworthy ML by providing a formal, axiomatic approach to causal explainability, which is incremental as it builds on existing game-theoretic measures.
The paper tackles the problem of explaining black-box model decisions by proposing three explanation measures that aggregate all but-for causes into feature importance weights, bridging model explanations, game-theoretic influence, and causal analysis, with practical analysis on the Adult-Income dataset.
Explaining the decisions of black-box models is a central theme in the study of trustworthy ML. Numerous measures have been proposed in the literature; however, none of them take an axiomatic approach to causal explainability. In this work, we propose three explanation measures which aggregate the set of all but-for causes -- a necessary and sufficient explanation -- into feature importance weights. Our first measure is a natural adaptation of Chockler and Halpern's notion of causal responsibility, whereas the other two correspond to existing game-theoretic influence measures. We present an axiomatic treatment for our proposed indices, showing that they can be uniquely characterized by a set of desirable properties. We also extend our approach to derive a new method to compute the Shapley-Shubik and Banzhaf indices for black-box model explanations. Finally, we analyze and compare the necessity and sufficiency of all our proposed explanation measures in practice using the Adult-Income dataset. Thus, our work is the first to formally bridge the gap between model explanations, game-theoretic influence, and causal analysis.