ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniques

TL;DR

ReX is a framework that enhances local explanation techniques for machine learning models with variable-length inputs by incorporating temporal information, leading to more accurate and understandable explanations.

Contribution

ReX introduces a novel way to include temporal data in model-agnostic explanations by modifying sampling and features, applicable to multiple explanation methods.

Findings

Significantly improves explanation fidelity.

Outperforms model-specific techniques on target models.

Enhances user understanding of model behavior.

Abstract

Existing local model-agnostic explanation techniques are ineffective for machine learning models that consider inputs of variable lengths, as they do not consider temporal information embedded in these models. To address this limitation, we propose \textsc{ReX}, a general framework for incorporating temporal information in these techniques. Our key insight is that these techniques typically learn a model surrogate by sampling model inputs and outputs, and we can incorporate temporal information in a uniform way by only changing the sampling process and the surrogate features. We instantiate our approach on three popular explanation techniques: Anchors, LIME, and Kernel SHAP. To evaluate the effectiveness of \textsc{ReX}, we apply our approach to six models in three different tasks. Our evaluation results demonstrate that our approach 1) significantly improves the fidelity of explanations, making model-agnostic techniques outperform a state-of-the-art model-specific technique on its target model, and 2) helps end users better understand the models' behaviors.