BELLA: Black-box model Explanations by Local Linear Approximations
Abstract: Understanding the decision-making process of black-box models has become not just a legal requirement, but also an additional way to assess their performance. However, the state of the art post-hoc explanation approaches for regression models rely on synthetic data generation, which introduces uncertainty and can hurt the reliability of the explanations. Furthermore, they tend to produce explanations that apply to only very few data points. In this paper, we present BELLA, a deterministic model-agnostic post-hoc approach for explaining the individual predictions of regression black-box models. BELLA provides explanations in the form of a linear model trained in the feature space. BELLA maximizes the size of the neighborhood to which the linear model applies so that the explanations are accurate, simple, general, and robust. BELLA can produce both factual and counterfactual explanations.
Submission Length: Regular submission (no more than 12 pages of main content)
Previous TMLR Submission Url: https://openreview.net/forum?id=GTEdYVw3wE
Changes Since Last Submission: Hi,
we would like to thank the reviewers again for their detailed reviews. We have now made all requested changes in the paper. To ease the reviewing, we have marked all changes in blue. (The changes in notation requested by one reviewer are scattered throughout the paper, and hence not in blue. For the variables $i$ and $n$, a change made the text less readable, and they thus remain general-purpose locally defined and locally used indexes and numbers, respectively. All other notation was changed as requested.)
We believe that we answered all requests, either in our rebuttal for each reviewer, or in both the rebuttal and the new version of the paper.
We are happy to answer any additional questions you may have, and we are very grateful that you are reviewing our paper.
Sincerely,
the authors
Assigned Action Editor: ~Dennis_Wei1
Submission Number: 3466
Loading