Faith-Shap: The Faithful Shapley Interaction Index
Che-Ping Tsai, Chih-Kuan Yeh, Pradeep Ravikumar

TL;DR
Faith-Shap introduces a unique, axiomatic interaction index based on faithful linear approximations, extending Shapley values to feature interactions in machine learning explanations with computational efficiency.
Contribution
The paper proposes a novel, axiomatic-based method called Faith-Shap for assigning feature interaction attributions, ensuring faithfulness and uniqueness in explanations.
Findings
Faith-Shap is computationally efficient.
It provides a unique interaction index satisfying key axioms.
Illustrative experiments demonstrate its practical utility.
Abstract
Shapley values, which were originally designed to assign attributions to individual players in coalition games, have become a commonly used approach in explainable machine learning to provide attributions to input features for black-box machine learning models. A key attraction of Shapley values is that they uniquely satisfy a very natural set of axiomatic properties. However, extending the Shapley value to assigning attributions to interactions rather than individual players, an interaction index, is non-trivial: as the natural set of axioms for the original Shapley values, extended to the context of interactions, no longer specify a unique interaction index. Many proposals thus introduce additional less ''natural'' axioms, while sacrificing the key axiom of efficiency, in order to obtain unique interaction indices. In this work, rather than introduce additional conflicting axioms, we…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsBayesian Modeling and Causal Inference · Game Theory and Voting Systems · Multi-Criteria Decision Making
