提出新型抗噪损失函数，提升标签噪声下的模型鲁棒性。
Variation-Bounded Loss for Noise-Tolerant Learning
- 引入变化率衡量损失函数抗噪能力，设计有界变化率的损失族。
- 理论证明变化率越小越鲁棒，实验验证在多个数据集上效果更优。
- 可改造常见损失函数，适合标签含噪场景的应用部署。
消除标签噪声对监督学习的负面影响是长期挑战。稳健损失函数成为主流解决方案。本文提出一种与损失函数鲁棒性相关的新型属性——变化率，并构建一类新损失函数，称为变化率有界损失（Variation-Bounded Loss, VBL），其特点是变化率受限。我们提供了变化率的理论分析，证明较小的变化率能带来更好的鲁棒性。此外，发现变化率可放宽对称性条件，提供更简洁的路径实现非对称性。基于此，我们将若干常用损失函数重构为变化率有界形式以用于实际。在多个数据集上的正向实验验证了该方法的有效性和灵活性。
原文摘要 · Abstract (English)
Mitigating the negative impact of noisy labels has been aperennial issue in supervised learning. Robust loss functions have emerged as a prevalent solution to this problem. In this work, we introduce the Variation Ratio as a novel property related to the robustness of loss functions, and propose a new family of robust loss functions, termed Variation-Bounded Loss (VBL), which is characterized by a bounded variation ratio. We provide theoretical analyses of the variation ratio, proving that a smaller variation ratio would lead to better robustness. Furthermore, we reveal that the variation ratio provides a feasible method to relax the symmetric condition and offers a more concise path to achieve the asymmetric condition. Based on the variation ratio, we reformulate several commonly used loss functions into a variation-bounded form for practical applications. Positive experiments on various datasets exhibit the effectiveness and flexibility of our approach.
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。