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.

本文提出了一种名为Predict then Interpolate (PI)的算法，通过使用分类器在一个环境中训练并将其用于另一个环境中进行预测的错误来揭示不稳定的相关性，然后使用群组分布稳健优化来最小化所有插值的最坏情况风险，通过实验证明，该算法在文本分类和图像分类中均具有优越的性能。

预测再插值：一种学习稳定分类器的简单算法