无需额外数据，用置信度差值提升噪声标签下的模型鲁棒性。
Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise
- 通过批次内校准的分位数阈值，筛选高置信度样本进行训练。
- 在6个基准上最高提升3.39%准确率，降低20.44%预测集大小。
- 适用于各类分类器，尤其适合无干净数据或先验信息的场景。
现有噪声标签学习方法通常依赖噪声转移矩阵、干净子集或预训练特征提取器等特权信息，而这些资源恰恰在需要鲁棒性时最缺乏。本文提出共形置信度风险最小化（CMRM），一种即插即用的封装框架，仅通过添加一个基于分位数校准的正则项，即可在不修改训练流程的前提下提升任意分类损失在标签噪声下的表现。CMRM测量真实标签与竞争标签间的置信度差距，并以每批样本独立估计的共形分位数作为阈值，聚焦高置信度样本，抑制可能被误标的数据。我们推导了在任意标签噪声下对边际分布温和正则条件成立的学习界。在五种基础方法和六个基准（含合成与真实噪声）上的实验表明，CMRM持续提升准确率（最高+3.39%），减少共形预测集合大小（最多-20.44%），且在0%噪声下性能不降，证明其捕捉到了现有机制未利用的跨方法不确定性信号。
原文摘要 · Abstract (English)
Most methods for learning with noisy labels require privileged knowledge such as noise transition matrices, clean subsets or pretrained feature extractors, resources typically unavailable when robustness is most needed. We propose Conformal Margin Risk Minimization (CMRM), a plug-and-play envelope framework that improves any classification loss under label noise by adding a single quantile-calibrated regularization term, with no privileged knowledge or training pipeline modification. CMRM measures the confidence margin between the observed label and competing labels, and thresholds it with a conformal quantile estimated per batch to focus training on high-margin samples while suppressing likely mislabeled ones. We derive a learning bound for CMRM under arbitrary label noise requiring only mild regularity of the margin distribution. Across five base methods and six benchmarks with synthetic and real-world noise, CMRM consistently improves accuracy (up to +3.39%), reduces conformal prediction set size (up to -20.44%) and does not hurt under 0% noise, showing that CMRM captures a method-agnostic uncertainty signal that existing mechanisms did not exploit.
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。