Editing a classifier by rewriting its prediction rules

Part of Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021)

Paper Supplemental

Bibtek download is not available in the pre-proceeding


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


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.