Editing a classifier by rewriting its prediction rules

Shibani Santurkar, Dimitris Tsipras, Mahalaxmi Elango, David Bau, Antonio Torralba, Aleksander Madry

Keywords: model debugging, spurious correlations, robustness

TL;DR: We propose a method that allows users to rewrite high-level predictions rules with virtually no additional data collection.

Abstract: We propose a methodology for modifying the behavior of a classifier by directly rewriting its prediction rules. Our method requires virtually no additional data collection and can be applied to a variety of settings, including adapting a model to new environments, and modifying it to ignore spurious features.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://github.com/MadryLab/EditingClassifiers