Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
This work addresses the need for more principled and robust feature attribution methods in explainable AI (XAI), though it appears incremental by extending existing cooperative game theory frameworks.
The paper tackles the problem of feature attribution in machine learning interpretability by moving beyond Shapley values, proposing a broader use of cooperative game theory tools like Weber and Harsanyi sets to offer richer interpretative flexibility.
Cooperative game theory has become a cornerstone of post-hoc interpretability in machine learning, largely through the use of Shapley values. Yet, despite their widespread adoption, Shapley-based methods often rest on axiomatic justifications whose relevance to feature attribution remains debatable. In this paper, we revisit cooperative game theory from an interpretability perspective and argue for a broader and more principled use of its tools. We highlight two general families of efficient allocations, the Weber and Harsanyi sets, that extend beyond Shapley values and offer richer interpretative flexibility. We present an accessible overview of these allocation schemes, clarify the distinction between value functions and aggregation rules, and introduce a three-step blueprint for constructing reliable and theoretically-grounded feature attributions. Our goal is to move beyond fixed axioms and provide the XAI community with a coherent framework to design attribution methods that are both meaningful and robust to shifting methodological trends.