GRANITE: A Generalized Regional Framework for Identifying Agreement in Feature-Based Explanations

MCML Authors

Maximilian Muschalik

→ Group Eyke Hüllermeier
 Artificial Intelligence and Machine Learning

Fabian Fumagalli

Prof. Dr.

Thomas Bayes Fellow

Statistical Learning and Data Science

Abstract

Feature-based explanation methods aim to quantify how features influence the model's behavior, either locally or globally, but different methods often disagree, producing conflicting explanations. This disagreement arises primarily from two sources: how feature interactions are handled and how feature dependencies are incorporated. We propose GRANITE, a generalized regional explanation framework that partitions the feature space into regions where interaction and distribution influences are minimized. This approach aligns different explanation methods, yielding more consistent and interpretable explanations. GRANITE unifies existing regional approaches, extends them to feature groups, and introduces a recursive partitioning algorithm to estimate such regions. We demonstrate its effectiveness on real-world datasets, providing a practical tool for consistent and interpretable feature explanations.

misc HLM+26

---

Preprint

Jan. 2026

---

Authors

J. Herbinger • G. Laberge • M. Muschalik • Y. Pequignot • M. N. Wright • F. Fumagalli

---

Links

arXiv

---

Research Areas

 A1 | Statistical Foundations & Explainability

 A3 | Computational Models