Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedCorr: Multi-Stage Federated Learning for Label Noise Correction
Jingyi Xu, Zihan Chen, Tony Q.S. Quek, Kai Fong Ernest Chong
Check 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 |
|---|---|---|---|
| Apply FedCorr's multi-stage identification and label correction framework | federated training · CIFAR-10 IID, (ρ,τ)=(0.8,0.5) | best test accuracy (%): 80.59±1.49 -> 90.59±0.70 | Improved |
| Apply FedCorr's multi-stage identification and label correction framework | federated training · CIFAR-100 IID, (ρ,τ)=(0.8,0.5) | best test accuracy (%): 51.24±1.60 -> 59.10±5.12 | Improved |
| Use the proposed non-IID client partition with FedCorr | CIFAR-10 federated learning · CIFAR-10 non-IID, (p,αDir)=(0.3,10), (ρ,τ)=(0.6,0.5) | best test accuracy (%): 73.86±2.41 -> 81.57±3.68 | Improved |
| Add label correction (ablation) | FedCorr · CIFAR-10 IID, (ρ,τ)=(0.8,0.5) | best test accuracy (%): 88.77±1.10 -> 90.59±0.70 | Improved |
| Use fraction scheduling (ablation) | FedCorr · CIFAR-10 IID, (ρ,τ)=(0.8,0.5) | best test accuracy (%): 72.71±5.03 -> 90.59±0.70 | Improved |
| Add adaptive local proximal regularization (ablation) | FedCorr · CIFAR-10 IID, (ρ,τ)=(0.8,0.5) | best test accuracy (%): 88.74±1.72 -> 90.59±0.70 | Improved |
| Add the finetuning stage (ablation) | FedCorr · CIFAR-10 IID, (ρ,τ)=(0.8,0.5) | best test accuracy (%): 83.81±2.59 -> 90.59±0.70 | Improved |
| Add the usual training stage (ablation) | FedCorr · CIFAR-10 IID, (ρ,τ)=(0.8,0.5) | best test accuracy (%): 88.97±1.37 -> 90.59±0.70 | Improved |
| Add mixup augmentation (ablation) | FedCorr · CIFAR-10 IID, (ρ,τ)=(0.8,0.5) | best test accuracy (%): 83.29±1.78 -> 90.59±0.70 | Improved |
| Use cumulative rather than per-iteration LID scores for identifying noisy clients | FedCorr · CIFAR-10 IID, label-noise client identification | separation of clean and noisy clients | Improved |
| Apply the first two FedCorr stages before another FL method | FedDyn, Median, and PoC · CIFAR-10/100, multiple noisy-client ratios | best test accuracy (%) | Improved |
Later papers that compared with this method
7 later accepted papers report FedCorr as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.
- Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy Labels (ICML 2026 · better on 4 of 4 shared results)
- FedClean: A General Robust Label Noise Correction for Federated Learning (ICML 2025 · better on 1 of 7 shared results)
- FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning (AAAI 2024 · better on 7 of 11 shared results)
- Federated Label-Noise Learning with Local Diversity Product Regularization (AAAI 2024 · better on 8 of 8 shared results)
- Federated Learning with Extremely Noisy Clients via Negative Distillation (AAAI 2024 · better on 5 of 6 shared results)
- Federated Partial Label Learning with Local-Adaptive Augmentation and Regularization (AAAI 2024 · better on 5 of 5 shared results)
- Federated Learning with Local Openset Noisy Labels (ECCV 2024 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FedClean: A General Robust Label Noise Correction for Federated Learning (ICML 2025 · similarity 0.94)
- FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels (AAAI 2024 · similarity 0.94)
- FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning (AAAI 2024 · similarity 0.93)
- (FL)$^2$: Overcoming Few Labels in Federated Semi-Supervised Learning (NeurIPS 2024 · similarity 0.91)
- Federated Learning with Extremely Noisy Clients via Negative Distillation (AAAI 2024 · similarity 0.91)
- Federated Label-Noise Learning with Local Diversity Product Regularization (AAAI 2024 · similarity 0.90)
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.
