发表机构
School of Mathematics, Harbin Institute of Technology; School of Earth and Space Sciences, Peking University（哈尔滨工业大学数学学院; 北京大学地球与空间科学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对噪声标签学习问题，提出从单变量基函数构建鲁棒多类损失的框架，开发两种方案并分析其性质，推导理论标准，所提损失在多噪声设置下经实验验证有竞争力或更优。
AI 中文摘要
有噪声标签学习是训练可靠深度神经网络的基本问题。鲁棒损失函数是减轻标签噪声负面影响的直接有效方法。但现有多数鲁棒损失直接针对最终多类目标设计，难以系统表征和扩展其鲁棒性。本文提出从单变量基函数构建鲁棒多类损失的通用框架，通过定义映射算子，可根据基函数简单性质表征诱导损失的鲁棒性。开发了两种互补构建方案，分析了其对称和不对称性质并推导充分条件，为噪声鲁棒损失设计提供理论标准。该框架还为构建对称损失提供新途径。在合成和真实世界噪声标签基准上的大量实验表明，所提损失在各种噪声设置下具有竞争力或更优性能。
英文摘要
Learning with noisy labels is a fundamental problem in training reliable deep neural networks. Robust loss functions provide a direct and effective way to mitigate the adverse effects of label noise. However, most existing robust losses are designed directly at the level of the final multiclass objective, which makes it difficult to systematically characterize and extend their robustness properties. In this paper, we propose a general framework that constructs robust multiclass losses from univariate base functions. By defining mapping operators from base functions to multiclass losses, the robustness of the induced losses can be characterized through simple properties of the base functions. We develop two complementary construction schemes, Target Separation and Binary Reduction, corresponding to inter-class independent and inter-class dependent formulations, respectively. For both schemes, we analyze their symmetry and asymmetry properties and derive corresponding sufficient conditions, which provide theoretical criteria for noise-robust loss design. The proposed framework also provides a new route to constructing symmetric losses, serving as a complement to normalization-based symmetric loss designs. Extensive experiments on synthetic and real-world noisy-label benchmarks demonstrate that the proposed losses achieve competitive or superior performance under various noise settings.
