MAnchors: Memorization-Based Acceleration of Anchors via Rule Reuse and Transformation

TL;DR

This paper introduces MAnchors, a memorization-based framework that accelerates the Anchors explanation technique by reusing and transforming rules, significantly reducing computation time while maintaining explanation quality across various data types.

Contribution

The paper presents a novel memorization and rule transformation approach that enhances the efficiency of Anchors explanations without sacrificing fidelity or interpretability.

Findings

Significantly reduces explanation generation time.

Maintains high fidelity and interpretability.

Effective across tabular, text, and image datasets.

Abstract

Anchors is a popular local model-agnostic explanation technique whose applicability is limited by its computational inefficiency. To address this limitation, we propose a memorization-based framework that accelerates Anchors while preserving explanation fidelity and interpretability. Our approach leverages the iterative nature of Anchors' algorithm which gradually refines an explanation until it is precise enough for a given input by storing and reusing intermediate results obtained during prior explanations. Specifically, we maintain a memory of low-precision, high-coverage rules and introduce a rule transformation framework to adapt them to new inputs: the horizontal transformation adapts a pre-trained explanation to the current input by replacing features, and the vertical transformation refines the general explanation until it is precise enough for the input. We evaluate our method across tabular, text, and image datasets, demonstrating that it significantly reduces explanation generation time while maintaining fidelity and interpretability, thereby enabling the practical adoption of Anchors in time-sensitive applications.