Variation-Bounded Loss for Noise-Tolerant Learning
This addresses the issue of label noise for machine learning practitioners, offering a flexible method with theoretical backing, though it appears incremental as it builds on existing robust loss functions.
The paper tackles the problem of noisy labels in supervised learning by proposing Variation-Bounded Loss (VBL), a family of robust loss functions based on a novel Variation Ratio property, and shows its effectiveness in experiments on various datasets.
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.