BELLA: Black-box model Explanations by Local Linear Approximations

Nedeljko Radulovic, Albert Bifet, Fabian M. Suchanek

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.

Submission Length: Regular submission (no more than 12 pages of main content)

Previous TMLR Submission Url: https://openreview.net/forum?id=UMi289YXdD

Changes Since Last Submission:

Dear editors,

thank you for managing the review process of our submission! We are submitting here the camera ready version of our paper.

Sincerely,

the authors

Code: https://github.com/nedRad88/BELLA/

Assigned Action Editor: ~Dennis_Wei1

Submission Number: 4575