1. mixup: Beyond empirical risk minimization;hongyi;International Conference on Learning Representations,0
2. A reputation mechanism is all you need: Collaborative fairness and adversarial robustness in federated learning;xu;International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML(FL-ICML'21),0
3. Training classifiers that are universally robust to all label noise levels;jingyi;2021 International Joint Conference on Neural Networks (IJCNN),0
4. Learning from massive noisy labeled data for image classification;xiao;Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,0
5. Part-dependent label noise: Towards instance-dependent label noise;xia;NeurIPS,2020