On Symmetric Losses for Learning from Corrupted Labels

2019/01/27 by Nontawat Charoenphakdee, Charoenphakdee, Nontawat, Jongyeong Lee +3 · 5 citations
Computer Science · Mathematics · #FOS: Computer and information sciences #Imbalanced Data Classification Techniques #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Machine Learning and Data Classification #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1901.09314

ICML2019 with minor typo fixes

openalex publication_date 2019/01/27 · arxiv created 2019/09/07 · arxiv updated 2019/09/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper aims to provide a better understanding of a symmetric loss. First, we emphasize that using a symmetric loss is advantageous in the balanced error rate (BER) minimization and area under the receiver operating characteristic curve (AUC) maximization from corrupted labels. Second, we prove general theoretical properties of symmetric losses, including a classification-calibration condition, excess risk bound, conditional risk minimizer, and AUC-consistency condition. Third, since all nonnegative symmetric losses are non-convex, we propose a convex barrier hinge loss that benefits significantly from the symmetric condition, although it is not symmetric everywhere. Finally, we conduct experiments to validate the relevance of the symmetric condition.

Citations

• Sparse Robust Classification via the Kernel Mean
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms
• Learning from Uncertain Similarity and Unlabeled Data
• Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition
• On Symmetric Losses for Robust Policy Optimization with Noisy Preferences
• Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel-Young Losses

Related

• A Symmetric Loss Perspective of Reliable Machine Learning
• Learning with Symmetric Label Noise: The Importance of Being Unhinged
• An Exploration into why Output Regularization Mitigates Label Noise
• Making Convex Loss Functions Robust to Outliers using e-Exponentiated Transformation
• Minimizing The Misclassification Error Rate Using a Surrogate Convex Loss