English

Stability theory of game-theoretic group feature explanations for machine learning models

Computer Science and Game Theory 2024-08-13 v6 Probability

Abstract

In this article, we study feature attributions of Machine Learning (ML) models originating from linear game values and coalitional values defined as operators on appropriate functional spaces. The main focus is on random games based on the conditional and marginal expectations. The first part of our work formulates a stability theory for these explanation operators by establishing certain bounds for both marginal and conditional explanations. The differences between the two games are then elucidated, such as showing that the marginal explanations can become discontinuous on some naturally-designed domains, while the conditional explanations remain stable. In the second part of our work, group explanation methodologies are devised based on game values with coalition structure, where the features are grouped based on dependencies. We show analytically that grouping features this way has a stabilizing effect on the marginal operator on both group and individual levels, and allows for the unification of marginal and conditional explanations. Our results are verified in a number of numerical experiments where an information-theoretic measure of dependence is used for grouping.

Keywords

Cite

@article{arxiv.2102.10878,
  title  = {Stability theory of game-theoretic group feature explanations for machine learning models},
  author = {Alexey Miroshnikov and Konstandinos Kotsiopoulos and Khashayar Filom and Arjun Ravi Kannan},
  journal= {arXiv preprint arXiv:2102.10878},
  year   = {2024}
}

Comments

82 pages, 43 figures. Typos fixed. Some technical results have been improved

R2 v1 2026-06-23T23:23:28.800Z