Research map / Learning theory and algorithms / Prediction and decision losses
Learning With Multiclass AUC: Theory and Algorithms
Zhiyong Yang, Qianqian Xu, Shilong Bao, Xiaochun Cao, Qingming Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use exponential-loss multiclass AUC optimization instead of cross-entropy | deep model · iNaturalist2017 | MAUC: 66.84 -> 84.87 | Improved |
| use exponential-loss multiclass AUC optimization instead of cross-entropy | deep model · CIFAR-100-Imb | MAUC: 59.80 -> 62.08 | Improved |
| use exponential-loss multiclass AUC optimization instead of cross-entropy | deep model · User-Imb | MAUC: 55.26 -> 60.94 | Improved |
| use squared-loss multiclass AUC optimization instead of DeepAUC | deep model · iNaturalist2017 | MAUC: 62.48 -> 79.67 | Improved |
| use exponential-loss multiclass AUC optimization instead of DeepAUC | deep model · User-Imb | MAUC: 59.93 -> 60.94 | Improved |
| use hinge loss rather than cross-entropy in the MAUC framework | deep model · CIFAR-100-Imb | MAUC: 59.80 -> 59.64 | Hurt |
| use hinge loss instead of exponential loss in the MAUC framework | deep model · iNaturalist2017 | MAUC: 84.87 -> 79.16 | Hurt |
| add BorderlineSMOTE oversampling to CE baseline | CE · iNaturalist2017 | MAUC: 66.84 -> 78.18 | Improved |
| add BorderlineSMOTE oversampling to CE baseline | CE · CIFAR-100-Imb | MAUC: 59.80 -> 59.07 | Hurt |
| add TomekLinks undersampling to CE baseline | CE · User-Imb | MAUC: 55.26 -> 52.99 | Hurt |
| add class-balanced reweighting to cross-entropy (CBCE) | CE · User-Imb | MAUC: 55.26 -> 58.91 | Improved |
| add class-balanced reweighting to cross-entropy (CBCE) | CE · iNaturalist2017 | MAUC: 66.84 -> 77.71 | Improved |
Closest papers by meaning
- Towards Decision-Friendly AUC: Learning Multi-Classifier with AUCµ (AAAI 2023 · similarity 0.95)
- AUCμ: A Performance Metric for Multi-Class Machine Learning Models (ICML 2019 · similarity 0.90)
- A Closer Look at AUROC and AUPRC under Class Imbalance (NeurIPS 2024 · similarity 0.88)
- Interplay of ROC and Precision-Recall AUCs: Theoretical Limits and Practical Implications in Binary Classification (ICML 2024 · similarity 0.88)
- AUC Optimization from Multiple Unlabeled Datasets (AAAI 2024 · similarity 0.88)
- Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
