mlsanityData to 7 Oct 2026

FedCorr: Multi-Stage Federated Learning for Label Noise Correction

arXiv 2204.04677 ↗First posted 10 Apr 2022cs.LG cs.AI cs.CVcited by 61

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is a privacy-preserving distributed learning paradigm that enables clients to jointly train a global model. In real-world FL implementations, client data could have label noise, and different clients could have vastly different label noise levels. Although there exist methods in centralized learning for tackling label noise, such methods do not perform well on heterogeneous label noise in FL settings, due to the typically smaller sizes of client datasets and data privacy requirements in FL. In this paper, we propose textttFedCorr, a general multi-stage framework to tackle heterogeneous label noise in FL, without making any assumptions on the noise models of local clients, while still maintaining client data privacy. In particular, (1) textttFedCorr dynamically identifies noisy clients by exploiting the dimensionalities of the model prediction subspaces independently measured on all clients, and then identifies incorrect labels on noisy clients based on per-sample losses. To deal with data heterogeneity and to increase training stability, we propose an adaptive local proximal regularization term that is based on estimated local noise levels. (2) We further finetune the global model on identified clean clients and correct the noisy labels for the remaining noisy clients after finetuning. (3) Finally, we apply the usual training on all clients to make full use of all local data. Experiments conducted on CIFAR-10/100 with federated synthetic label noise, and on a real-world noisy dataset, Clothing1M, demonstrate that textttFedCorr is robust to label noise and substantially outperforms the state-of-the-art methods at multiple noise levels.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). Builds on 31 of its 43 references that are in the map. First posted on arXiv 10 Apr 2022.

Builds on

31 of 43 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  6. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  7. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  8. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  9. 2020Adaptive Federated Optimizationcited by 1,036
  10. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  11. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  12. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
19 more
  1. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  2. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  3. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  4. 2021Federated Learning Based on Dynamic Regularizationcited by 555
  5. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  6. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  7. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  8. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  9. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 196
  10. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  11. 2020Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Datacited by 125
  12. 2020A Survey of Label-noise Representation Learning: Past, Present and Futurecited by 121
  13. 2019Attack-Resistant Federated Learning with Residual-based Reweightingcited by 40
  14. 2020Robust Federated Learning with Noisy Labelscited by 40
  15. 2020A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learningcited by 38
  16. 2020FOCUS: Dealing with Label Quality Disparity in Federated Learningcited by 36
  17. 2021Robust Federated Learning with Attack-Adaptive Aggregationcited by 17
  18. 2021Dynamic Attention-based Communication-Efficient Federated Learningcited by 9
  19. 2021Training Classifiers that are Universally Robust to All Label Noise Levelscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 15; 2024: 18; 2025: 14; 2026: 10.

61 papers.

Sort:

By area:

  1. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
  2. 2023FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneitycited by 33
  3. 2024Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domainscited by 27
  4. 2023Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancercited by 17
  5. 2023FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clusteringcited by 15
  6. 2023FedA3I: Annotation Quality-Aware Aggregation for Federated Medical Image Segmentation against Heterogeneous Annotation Noisecited by 14
  7. 2022Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labelscited by 13
  8. 2023FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labelscited by 13
  9. 2023Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clientscited by 12
  10. 2023Federated Learning with Extremely Noisy Clients via Negative Distillationcited by 12
  11. 2024AdaFed: Fair Federated Learning via Adaptive Common Descent Directioncited by 12
  12. 2024Advances in Robust Federated Learning: A Survey with Heterogeneity Considerationscited by 12
38 more
  1. 2023FedNoisy: Federated Noisy Label Learning Benchmarkcited by 11
  2. 2023Federated Learning with Instance-Dependent Noisy Labelcited by 9
  3. 2023FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Thingscited by 8
  4. 2024Spectral Co-Distillation for Personalized Federated Learningcited by 8
  5. 2024FedFixer: Mitigating Heterogeneous Label Noise in Federated Learningcited by 8
  6. 2025S2FGL: Spatial Spectral Federated Graph Learningcited by 7
  7. 2025FNBench: Benchmarking Robust Federated Learning against Noisy Labelscited by 6
  8. 2022NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimensioncited by 5
  9. 2023FediOS: Decoupling Orthogonal Subspaces for Personalization in Feature-skew Federated Learningcited by 5
  10. 2024Federated Learning Under Attack: Exposing Vulnerabilities through Data Poisoning Attacks in Computer Networkscited by 5
  11. 2024FedMLP: Federated Multi-Label Medical Image Classification under Task Heterogeneitycited by 5
  12. 2023Entropy-driven Fair and Effective Federated Learningcited by 4
  13. 2024Federated Distillation for Medical Image Classification: Towards Trustworthy Computer-Aided Diagnosiscited by 4
  14. 2024Federated Learning Client Pruning for Noisy Labelscited by 4
  15. 2022Quantifying the Impact of Label Noise on Federated Learningcited by 3
  16. 2023Personalizing Federated Learning with Over-the-Air Computationscited by 3
  17. 2025FedEL: Federated Elastic Learning for Heterogeneous Devicescited by 3
  18. 2022FedRN: Exploiting k-Reliable Neighbors Towards Robust Federated Learningcited by 2
  19. 2024FedIA: Federated Medical Image Segmentation with Heterogeneous Annotation Completenesscited by 2
  20. 2024Collaboratively Learning Federated Models from Noisy Decentralized Datacited by 2
  21. 2025FedPCA: Noise-Robust Fair Federated Learning via Performance-Capacity Analysiscited by 2
  22. 2026FB-NLL: A Feature-Based Approach to Tackle Noisy Labels in Personalized Federated Learningcited by 2
  23. 2024Revisiting Early-Learning Regularization When Federated Learning Meets Noisy Labelscited by 1
  24. 2024FedSat: A Statistical Aggregation Approach for Class Imbalanced Clients in Federated Learningcited by 1
  25. 2024Heterogeneity-Aware Coordination for Federated Learning via Stitching Pre-trained blockscited by 1
  26. 2024Data Quality Control in Federated Instruction-tuning of Large Language Modelscited by 1
  27. 2025Energy-Efficient Federated Learning for AIoT using Clustering Methodscited by 1
  28. 2025Rethinking Federated Learning Over the Air: The Blessing of Scaling Upcited by 1
  29. 2026FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labelscited by 1
  30. 2023Price of Stability in Quality-Aware Federated Learningcited by 0
  31. 2024Fast convergence of a Federated Expectation-Maximization Algorithmcited by 0
  32. 2024Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy Labelscited by 0
  33. 2024Delayed Random Partial Gradient Averaging for Federated Learningcited by 0
  34. 2025Task-Agnostic Federation over Decentralized Data: Research Landscape and Visionscited by 0
  35. 2025Fair Federated Medical Image Classification Against Quality Shift via Inter-Client Progressive State Matchingcited by 0
  36. 2025FedTilt: Towards Multi-Level Fairness-Preserving and Robust Federated Learningcited by 0
  37. 2025FedEFC: Federated Learning Using Enhanced Forward Correction Against Noisy Labelscited by 0
  38. 2025Lightweight and Robust Federated Data Valuationcited by 0

50 most cited of 61 All 61 (JSON)