Editing a classifier by rewriting its prediction rules
2021-12-02NeurIPS 2021Code Available1· sign in to hype
Shibani Santurkar, Dimitris Tsipras, Mahalaxmi Elango, David Bau, Antonio Torralba, Aleksander Madry
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/madrylab/editingclassifiersOfficialIn paperpytorch★ 96
Abstract
We present a methodology for modifying the behavior of a classifier by directly rewriting its prediction rules. Our approach 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. Our code is available at https://github.com/MadryLab/EditingClassifiers .