Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients
Tian Wen, Zhiqin Yang, Yonggang Zhang, Xuefeng Jiang, Hao Peng, Yuwei Wang, Bo Han
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 |
|---|---|---|---|
| Add the noise absorption matrix (ablation) | FedRG · CIFAR-10 (4 noise scenarios) | Clean recall, CRA, accuracy | Improved |
| Add label-decoupled spherical (SimCLR) pretraining stage (ablation) | FedRG · CIFAR-10 (4 noise scenarios) | Accuracy, CRA | Improved |
| Use symmetric cross-entropy instead of standard CE (ablation) | FedRG · CIFAR-10 (4 noise scenarios) | Accuracy | Improved |
| Keep noise absorption matrix local (do not aggregate) (ablation) | FedRG · CIFAR-10 (4 noise scenarios) | Accuracy | Improved |
| Use FedRG instead of best baseline | SymmetricCE · CIFAR-10 symmetric globalized | Accuracy: 59.23 -> 63.29 | Improved |
| Use FedRG instead of FedSAM | FedSAM · SVHN pairflip globalized | Accuracy: 75.25 -> 80.62 | Improved |
| Use FedRG instead of SymmetricCE | SymmetricCE · CIFAR-100 symmetric globalized | Accuracy | Mixed |
| Increase number of semantic clusters (6 to 20) (ablation) | FedRG · CIFAR-10 symmetric globalized | Accuracy: 62.60 - 64.00 | No clear effect |
| Increase proportion of selected clients per round (ablation) | FedRG · CIFAR-10 symmetric globalized | Accuracy | Improved |
Closest papers by meaning
- FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning (AAAI 2024 · similarity 0.90)
- FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels (AAAI 2024 · similarity 0.89)
- (FL)$^2$: Overcoming Few Labels in Federated Semi-Supervised Learning (NeurIPS 2024 · similarity 0.89)
- FedClean: A General Robust Label Noise Correction for Federated Learning (ICML 2025 · similarity 0.89)
- Progressive Distribution Matching for Federated Semi-Supervised Learning (AAAI 2025 · similarity 0.87)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (NeurIPS 2025 · similarity 0.87)
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.
