Neural networks produced by standard training are known to suffer from poor accuracy on rare subgroups despite achieving high accuracy on average, due to the correlations between certain spurious features and labels. Previous approaches based on worst-group loss minimization (e.g. Group-DRO) are effective in improving worse-group accuracy but require expensive group annotations for all the training samples. In this paper, we focus on the more challenging and realistic setting where group annotations are only available on a small validation set or are not available at all. We propose BAM, a novel two-stage training algorithm: in the first stage, the model is trained using a bias amplification scheme via introducing a learnable auxiliary variable for each training sample; in the second stage, we upweight the samples that the bias-amplified model misclassifies, and then continue training the same model on the reweighted dataset. Empirically, BAM achieves competitive performance compared with existing methods evaluated on spurious correlation benchmarks in computer vision and natural language processing. Moreover, we find a simple stopping criterion based on minimum class accuracy difference that can remove the need for group annotations, with little or no loss in worst-group accuracy. We perform extensive analyses and ablations to verify the effectiveness and robustness of our algorithm in varying class and group imbalance ratios.

翻译：神经网络在标准训练下，由于某些虚假特征与标签之间的相关性，虽然平均准确率较高，但在罕见子组上准确率较低。以往基于最差组损失最小化的方法（如Group-DRO）能有效改善最差组准确率，但需要所有训练样本的昂贵组标注。本文聚焦于更具挑战性和现实性的场景，即组标注仅存在于小型验证集或完全不可用。我们提出一种新型两阶段训练算法BAM：第一阶段，通过为每个训练样本引入可学习辅助变量，采用偏差放大幅度方案训练模型；第二阶段，我们提高被偏差放大模型错误分类样本的权重，并在重新加权数据集上继续训练相同模型。实验表明，BAM在计算机视觉和自然语言处理领域的虚假相关性基准测试中，与现有方法相比取得了具有竞争力的性能。此外，我们发现基于最小类别准确率差异的简单停止准则，可消除对组标注的需求，且最差组准确率几乎无损失。我们通过大量分析和消融实验，验证了算法在不同类别和组不平衡比例下的有效性和鲁棒性。