aiqbench analysis
This research introduces a memorization-based framework to accelerate the Anchors model-agnostic explanation technique by reusing and transforming intermediate rules. By adapting pre-trained explanations through horizontal feature replacement and vertical refinement, the method significantly cuts generation time without sacrificing interpretability across tabular, text, and image datasets. This advancement addresses computational inefficiency in local explainable AI (XAI), making high-fidelity model interpretation viable for real-time applications.
MAnchors: Memorization-Based Acceleration of Anchors via Rule Reuse and Transformation
arXiv:2502.11068v3 Announce Type: replace-cross 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.
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.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2502.11068 [cs.LG]
(or arXiv:2502.11068v3 [cs.LG] for this version)
Full text under the publisher's open licence · 165 words