通过识别模型依赖虚假特征的样本，针对性地抑制相关神经元，提升模型鲁棒性。
Shortcut Mitigation via Spurious-Positive Samples
- 定位模型依赖虚假特征的少数关键样本
- 通过抑制中间层相关神经元，强制学习有效特征
- 无需额外标注或平衡数据，适用于真实场景
现有缓解捷径学习的方法通常依赖训练数据标注、组平衡的保留数据或训练集中包含所有属性与类别组合。但这些条件在实际中很少满足。本文提出一种目标化模型分析方法，识别出模型依赖虚假属性的小部分样本。基于这些样本和‘该特征不应用于预测’的推理，定位中间层中高度相关的神经元并进行正则化，确保模型依赖于有意义的特征而非错误原因，从而在不需额外平衡数据或标注的情况下提升模型鲁棒性。
原文摘要 · Abstract (English)
Shortcut mitigation strategies commonly rely on training data annotations, group-balanced held-out data or the presence of all groups, i.e., all combinations of (spurious) attributes and classes, in the training data. However, these requirements are rarely met in practice. We instead propose a method for targeted model analysis to identify a small set of instances in which the model relies on spurious attributes. Using that set and following ``this feature should not be used for prediction'' reasoning, we identify highly relevant neurons in an intermediate layer and regularize their impact. This ensures that models learn to depend on informative features rather than being right for the wrong reasons, thereby improving robustness without requiring additional balanced held-out data or annotations.
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。