Defining Locality for Surrogates in Post-hoc Interpretablity

TL;DR

This paper emphasizes the importance of defining the right locality in surrogate models for local explanations, proposing a boundary-centered sampling method to improve explanation accuracy and relevance.

Contribution

It introduces a novel approach that samples around the decision boundary rather than the prediction point, enhancing local surrogate explanations.

Findings

Boundary-centered sampling improves explanation fidelity.

The proposed method outperforms state-of-the-art approaches.

Evaluation on four UCI datasets confirms effectiveness.

Abstract

Local surrogate models, to approximate the local decision boundary of a black-box classifier, constitute one approach to generate explanations for the rationale behind an individual prediction made by the back-box. This paper highlights the importance of defining the right locality, the neighborhood on which a local surrogate is trained, in order to approximate accurately the local black-box decision boundary. Unfortunately, as shown in this paper, this issue is not only a parameter or sampling distribution challenge and has a major impact on the relevance and quality of the approximation of the local black-box decision boundary and thus on the meaning and accuracy of the generated explanation. To overcome the identified problems, quantified with an adapted measure and procedure, we propose to generate surrogate-based explanations for individual predictions based on a sampling centered on particular place of the decision boundary, relevant for the prediction to be explained, rather than on the prediction itself as it is classically done. We evaluate the novel approach compared to state-of-the-art methods and a straightforward improvement thereof on four UCI datasets.