An Exploration into why Output Regularization Mitigates Label Noise

Abstract

Label noise presents a real challenge for supervised learning algorithms. Consequently, mitigating label noise has attracted immense research in recent years. Noise robust losses is one of the more promising approaches for dealing with label noise, as these methods only require changing the loss function and do not require changing the design of the classifier itself, which can be expensive in terms of development time. In this work we focus on losses that use output regularization (such as label smoothing and entropy). Although these losses perform well in practice, their ability to mitigate label noise lack mathematical rigor. In this work we aim at closing this gap by showing that losses, which incorporate an output regularization term, become symmetric as the regularization coefficient goes to infinity. We argue that the regularization coefficient can be seen as a hyper-parameter controlling the symmetricity, and thus, the noise robustness of the loss function.

This paper will appear at CVPR 2021 workshop on learning from limited and imperfect data (L2ID)

References in corpus (7)

• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• On Exact Computation with an Infinitely Wide Neural Net
• Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey
• Noise Tolerance under Risk Minimization
• Normalized Loss Functions for Deep Learning with Noisy Labels
• Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels
• Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee