HyperSHAP: Shapley Values and Interactions for Explaining Hyperparameter Optimization

Marcel Wever; Maximilian Muschalik; Fabian Fumagalli; Marius Lindauer

AAAI 2026technical0 citations

HyperSHAP: Shapley Values and Interactions for Explaining Hyperparameter Optimization

Marcel Wever, Maximilian Muschalik, Fabian Fumagalli, Marius Lindauer

Abstract

Hyperparameter optimization (HPO) is a crucial step in achieving strong predictive performance. Yet, the impact of individual hyperparameters on model generalization is highly context-dependent, prohibiting a one-size-fits-all solution and requiring opaque HPO methods to find optimal configurations. However, the black-box nature of most HPO methods undermines user trust and discourages adoption. To address this, we propose a game-theoretic explainability framework for HPO based on Shapley values and interactions. Our approach provides an additive decomposition of a performance measure across hyperparameters, enabling local and global explanations of hyperparameters

BibTeX

@inproceedings{aaai2026_hypershapshapley,
  title = {HyperSHAP: Shapley Values and Interactions for Explaining Hyperparameter Optimization},
  author = {Marcel Wever and Maximilian Muschalik and Fabian Fumagalli and Marius Lindauer},
  booktitle = {AAAI 2026},
  year = {2026}
}