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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Haonan, Liu, Junhao, Zhang, Xin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908792633950208
author Yu, Haonan
Liu, Junhao
Zhang, Xin
author_facet Yu, Haonan
Liu, Junhao
Zhang, Xin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11068
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MAnchors: Memorization-Based Acceleration of Anchors via Rule Reuse and Transformation
Yu, Haonan
Liu, Junhao
Zhang, Xin
Machine Learning
Artificial Intelligence
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.
title MAnchors: Memorization-Based Acceleration of Anchors via Rule Reuse and Transformation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2502.11068