用收敛后扰动敏感性识别虚假相关样本，无需标签和调参。
Perturbation Sensitivity at Convergence: A Simple Signal for Identifying Spuriously Correlated Samples
- 收敛后对输入加扰动，脆弱样本更易误判。
- 用水鸟数据集测试，最差组准确率从57.3%提升至80.8%。
- 无需分组标签或早停，适合无标注场景的鲁棒训练。
在存在虚假相关性的数据上，经验风险最小化训练的模型虽整体准确率高，但在相关性不成立的子群体上表现差。现有方法依赖早期训练信号，需人工选择干预时间点，通常需分组标注的验证数据。本文发现：模型收敛后，损失不再区分两组时，符合虚假相关性的样本遵循统一分类规则，而其余样本则依赖个体输入的特定拟合，对扰动更敏感。对已收敛模型输入施加固定扰动，这些脆弱样本的预测被翻转的频率远高于前者。该方法每样本仅需两次前向传播，全程无需分组标注，也无需早停策略。用检测出的样本重平衡训练后，Waterbirds数据集最差组准确率从57.3%提升至80.8%，接近使用真实分组标签时的85.8%。
原文摘要 · Abstract (English)
Models trained by empirical risk minimization on data containing spurious correlations achieve high average accuracy while failing on subpopulations where the correlation does not hold. Existing methods for identifying the affected samples without group annotations rely on signals from early training, which requires locating the epoch at which to intervene, a hyperparameter typically selected using group-labeled validation data. We show that a usable signal is available after convergence, when loss no longer distinguishes the two populations. Samples consistent with the spurious correlation are classified by a shared rule, while the remaining samples are fit through configurations specific to individual inputs and are correspondingly more fragile. Applying a fixed perturbation to a converged model's inputs flips the predictions of the latter far more often than the former. The resulting procedure requires two forward passes per training sample, no group annotations at any stage, and no early-stopping epoch. Using the detected samples to rebalance training raises worst-group accuracy on Waterbirds from 57.3% to 80.8%, against 85.8% with ground-truth group labels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。