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

TL;DR

GRANITE is a unified framework that partitions feature space into regions to reconcile conflicting feature-based explanations, enhancing their consistency and interpretability across different methods.

Contribution

It introduces a generalized regional explanation framework that unifies and extends existing methods, incorporating feature groups and recursive partitioning for better explanation consistency.

Findings

Effective on real-world datasets

Produces more consistent explanations

Unifies regional explanation approaches

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.