Trust Regions for Explanations via Black-Box Probabilistic Certification

Amit Dhurandhar, Swagatam Haldar, Dennis Wei, Karthikeyan Natesan Ramamurthy

Primary Area: visualization or interpretation of learned representations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Explainable AI

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We formulate and propose (approximate) efficient solutions for a novel (and useful) problem of finding certified regions for explanations.

Abstract: Given the black box nature of machine learning models, a plethora of explainability methods have been developed to decipher the factors behind individual decisions. In this paper, we introduce a novel problem of black box (probabilistic) explanation certification. We ask the question: Given a black box model with only query access, an explanation for an example and a quality metric (viz. fidelity, stability), can we find the largest hypercube (i.e., $\ell_{\infty}$ ball) centered at the example such that when the explanation is applied to all examples within the hypercube, (with high probability) a quality criterion is met (viz. fidelity greater than some value)? Being able to efficiently find such a *trust region* has multiple benefits: i) insight into model behavior in a *region*, with a *guarantee*; ii) ascertained *stability* of the explanation; iii) *explanation reuse*, which can save time, energy and money by not having to find explanations for every example; and iv) a possible *meta-metric* to compare explanation methods. Our contributions include formalizing this problem, proposing solutions, providing theoretical guarantees for these solutions that are computable, and experimentally showing their efficacy on synthetic and real data.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1448