English

Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers

Machine Learning 2021-05-27 v1 Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition

Abstract

We propose Predict then Interpolate (PI), a simple algorithm for learning correlations that are stable across environments. The algorithm follows from the intuition that when using a classifier trained on one environment to make predictions on examples from another environment, its mistakes are informative as to which correlations are unstable. In this work, we prove that by interpolating the distributions of the correct predictions and the wrong predictions, we can uncover an oracle distribution where the unstable correlation vanishes. Since the oracle interpolation coefficients are not accessible, we use group distributionally robust optimization to minimize the worst-case risk across all such interpolations. We evaluate our method on both text classification and image classification. Empirical results demonstrate that our algorithm is able to learn robust classifiers (outperforms IRM by 23.85% on synthetic environments and 12.41% on natural environments). Our code and data are available at https://github.com/YujiaBao/Predict-then-Interpolate.

Keywords

Cite

@article{arxiv.2105.12628,
  title  = {Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers},
  author = {Yujia Bao and Shiyu Chang and Regina Barzilay},
  journal= {arXiv preprint arXiv:2105.12628},
  year   = {2021}
}

Comments

ICML 2021

R2 v1 2026-06-24T02:29:31.931Z