Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Idrissi, Marouane Il, Machado, Agathe Fernandes, Charpentier, Arthur
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915347016187904
author Idrissi, Marouane Il
Machado, Agathe Fernandes
Charpentier, Arthur
author_facet Idrissi, Marouane Il
Machado, Agathe Fernandes
Charpentier, Arthur
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13900
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
Idrissi, Marouane Il
Machado, Agathe Fernandes
Charpentier, Arthur
Machine Learning
Artificial Intelligence
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.
title Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.13900