有界调整与可靠性引导嵌入用于带噪声标签的不平衡学习
Bounded Adjustment with Reliability-Guided Embedding for Imbalanced Learning with Noisy Labels
- Indian Institute of Technology Indore（印度理工学院印多尔分校）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对类别不平衡与标签噪声的耦合问题，提出BARGE方法，结合有界先验调整得分与可靠性引导角度几何，无需噪声率，在多个基准上显著降低平均平衡错误。
AI中文摘要：
类别平衡学习和标签噪声会产生一种耦合的失效模式：频率校正可防止多数类主导决策规则，但可能放大被错误标记的少数类样本。我们提出了BARGE（有界调整与可靠性引导嵌入），这是一个单阶段目标函数，结合了有界、先验调整的密度功率得分与可靠性引导的角度几何。其分类得分在调整后的概率空间中是严格适当的，并在干净监督和真实类别先验下恢复平衡贝叶斯排序。在标签污染下，其有限范围限制了固定预测器处的分类风险扰动，而其logit梯度在模型自信地反驳给定标签时会下降。调整后的目标概率还对类别等量的特征紧凑性进行加权，并且一个单侧分离项阻止对齐的类别方向。BARGE既不需要噪声率也不需要转移矩阵，使用单个网络，并且推理保持不变。我们在CIFAR-10、CIFAR-100和Tiny ImageNet上，在长尾和阶梯不平衡、干净标签以及20%和40%随机错误标签替换下进行了评估。在12个干净设置中，BARGE总体排名第二，并在四个设置中达到最低错误率。在污染下，它在所有六个数据集-污染设置中实现了最低的平均平衡错误，将六个设置的平均值从最强竞争者的72.32%降低到70.00%。它还在每个污染标签设置中获得了最高的宏F1和宏AUPRC。消融研究表明，类别等量的角度紧凑性优于单独的有界得分。这些结果支持有界预测影响和可靠性引导几何作为不确定标签下不平衡学习的互补机制。
英文摘要：
Class-balanced learning and label noise create a coupled failure mode: frequency correction prevents majority classes from dominating the decision rule, but can amplify incorrectly labeled minority examples. We introduce BARGE (Bounded Adjustment with Reliability-Guided Embeddings), a single-stage objective combining a bounded, prior-adjusted density-power score with reliability-guided angular geometry. Its classification score is strictly proper in the adjusted probability space and recovers balanced Bayes ordering under clean supervision and the true class prior. Under label contamination, its finite range bounds classification-risk perturbation at a fixed predictor, while its logit gradient redescends when the model confidently contradicts the supplied label. The adjusted target probability also weights class-equal feature compactness, and a one-sided separation term discourages aligned class directions. BARGE requires neither a noise rate nor a transition matrix, uses one network, and leaves inference unchanged. We evaluate it on CIFAR-10, CIFAR-100, and Tiny ImageNet under long-tail and step imbalance, clean labels, and 20% and 40% random incorrect-label replacement. Across 12 clean settings, BARGE ranks second overall and attains the lowest error in four. Under corruption, it achieves the lowest mean balanced error in all six dataset-corruption settings, reducing the six-setting average from 72.32% for the strongest competitor to 70.00%. It also obtains the highest macro-F1 and macro-AUPRC in every corrupted-label setting. Ablations show that class-equal angular compactness improves on the bounded score alone. These results support bounded predictive influence and reliability-guided geometry as complementary mechanisms for imbalanced learning with uncertain labels.
