Approximating Score-based Explanation Techniques Using Conformal Regression

TL;DR

This paper introduces a method to efficiently approximate score-based explanation techniques like SHAP using regression models, with validity guarantees provided by conformal prediction, enabling faster and reliable explanations in time-critical applications.

Contribution

It proposes a novel approach combining regression models and conformal prediction to approximate explanations efficiently with validity guarantees.

Findings

Significant reduction in explanation computation time compared to TreeSHAP.

Approximate explanations maintain tightness and validity guarantees.

Method enables comparison and selection of explanation methods based on interval tightness.

Abstract

Score-based explainable machine-learning techniques are often used to understand the logic behind black-box models. However, such explanation techniques are often computationally expensive, which limits their application in time-critical contexts. Therefore, we propose and investigate the use of computationally less costly regression models for approximating the output of score-based explanation techniques, such as SHAP. Moreover, validity guarantees for the approximated values are provided by the employed inductive conformal prediction framework. We propose several non-conformity measures designed to take the difficulty of approximating the explanations into account while keeping the computational cost low. We present results from a large-scale empirical investigation, in which the approximate explanations generated by our proposed models are evaluated with respect to efficiency (interval size). The results indicate that the proposed method can significantly improve execution time compared to the fast version of SHAP, TreeSHAP. The results also suggest that the proposed method can produce tight intervals, while providing validity guarantees. Moreover, the proposed approach allows for comparing explanations of different approximation methods and selecting a method based on how informative (tight) are the predicted intervals.