Defining Locality for Surrogates in Post-hoc Interpretablity
This addresses the challenge of generating accurate explanations for black-box classifier predictions, which is crucial for users needing interpretability in AI systems, though it is incremental as it builds on existing surrogate-based methods.
The paper tackles the problem of defining the right locality for training local surrogate models in post-hoc interpretability, showing that this significantly impacts explanation accuracy, and proposes a novel sampling method centered on the decision boundary, achieving improved results on four UCI datasets.
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.