Simple and Fast Group Robustness by Automatic Feature Reweighting

Shikai Qiu, Andres Potapczynski, Pavel Izmailov, Andrew Gordon Wilson

Research output: Contribution to journalConference articlepeer-review


A major challenge to out-of-distribution generalization is reliance on spurious features - patterns that are predictive of the class label in the training data distribution, but not causally related to the target. Standard methods for reducing the reliance on spurious features typically assume that we know what the spurious feature is, which is rarely true in the real world. Methods that attempt to alleviate this limitation are complex, hard to tune, and lead to a significant computational overhead compared to standard training. In this paper, we propose Automatic Feature Reweighting (AFR), an extremely simple and fast method for updating the model to reduce the reliance on spurious features. AFR retrains the last layer of a standard ERM-trained base model with a weighted loss that emphasizes the examples where the ERM model predicts poorly, automatically upweighting the minority group without group labels. With this simple procedure, we improve upon the best reported results among competing methods trained without spurious attributes on several vision and natural language classification benchmarks, using only a fraction of their compute.

Original languageEnglish (US)
Pages (from-to)28448-28467
Number of pages20
JournalProceedings of Machine Learning Research
StatePublished - 2023
Event40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: Jul 23 2023Jul 29 2023

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability


Dive into the research topics of 'Simple and Fast Group Robustness by Automatic Feature Reweighting'. Together they form a unique fingerprint.

Cite this