FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity
| Autor: | Wu, Nannan, Yu, Li, Jiang, Xuefeng, Cheng, Kwang-Ting, Yan, Zengqiang |
|---|---|
| Rok vydání: | 2023 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Federated noisy label learning (FNLL) is emerging as a promising tool for privacy-preserving multi-source decentralized learning. Existing research, relying on the assumption of class-balanced global data, might be incapable to model complicated label noise, especially in medical scenarios. In this paper, we first formulate a new and more realistic federated label noise problem where global data is class-imbalanced and label noise is heterogeneous, and then propose a two-stage framework named FedNoRo for noise-robust federated learning. Specifically, in the first stage of FedNoRo, per-class loss indicators followed by Gaussian Mixture Model are deployed for noisy client identification. In the second stage, knowledge distillation and a distance-aware aggregation function are jointly adopted for noise-robust federated model updating. Experimental results on the widely-used ICH and ISIC2019 datasets demonstrate the superiority of FedNoRo against the state-of-the-art FNLL methods for addressing class imbalance and label noise heterogeneity in real-world FL scenarios. Comment: Accepted by IJCAI 2023 (Main Track) |
| Databáze: | arXiv |
| Externí odkaz: |
|