Classifiers are biased when trained on biased datasets. As a remedy, we propose Learning to Split (ls), an algorithm for automatic bias detection. Given a dataset with input-label pairs, ls learns to split this dataset so that predictors trained on the training split generalize poorly to the testing split. This performance gap provides a proxy for measuring the degree of bias in the learned features and can therefore be used to reduce biases. Identifying non-generalizable splits is challenging as we don't have any explicit annotations about how to split. In this work, we show that the prediction correctness of the testing example can be used as a source of weak supervision: generalization performance will drop if we move examples that are predicted correctly away from the testing split, leaving only those that are mispredicted. We evaluate our approach on Beer Review, Waterbirds, CelebA and MNLI. Empirical results show that ls is able to generate astonishingly challenging splits that correlate with human-identified biases. Moreover, we demonstrate that combining robust learning algorithms (such as group DRO) with splits identified by ls enables automatic de-biasing. Compared with previous state-of-the-arts, we substantially improves the worst-group performance (23.4% on average) when the source of biases is unknown during training and validation.

中文翻译：

---

学习分裂自动偏差检测

在有偏差的数据集上训练时，分类器是有偏差的。作为一种补救措施，我们提出了学习分裂（ls），一种用于自动偏差检测的算法。给定一个带有输入-标签对的数据集，ls 学习分割这个数据集，以便在训练分割上训练的预测器很难泛化到测试分割。这种性能差距提供了衡量学习特征中偏差程度的代理，因此可用于减少偏差。识别不可泛化的拆分具有挑战性，因为我们没有任何关于如何拆分的明确注释。在这项工作中，我们表明测试示例的预测正确性可以用作弱监督的来源：如果我们将正确预测的示例从测试拆分中移开，而只留下预测错误的示例，泛化性能将会下降。我们评估了我们在 Beer Review、Waterbirds、CelebA 和 MNLI 上的方法。实证结果表明，ls 能够产生与人类识别的偏差相关的极具挑战性的分裂。此外，我们证明将稳健的学习算法（例如组 DRO）与 ls 识别的分割相结合，可以实现自动去偏。与以前的最先进技术相比，当在训练和验证期间偏差的来源未知时，我们显着提高了最差组的性能（平均 23.4%）。