mlsanityData to 7 Oct 2026

FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients

arXiv 2603.19722 ↗First posted 20 Mar 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) suffers from performance degradation due to the inevitable presence of noisy annotations in distributed scenarios. Existing approaches have advanced in distinguishing noisy samples from the dataset for label correction by leveraging loss values. However, noisy samples recognition relying on scalar loss lacks reliability for FL under heterogeneous scenarios. In this paper, we rethink this paradigm from a representation perspective and propose method~(Federated under Representation Gemometry), which follows the principle of ``representation geometry priority'' to recognize noisy labels. Firstly, method~creates label-agnostic spherical representations by using self-supervision. It then iteratively fits a spherical von Mises-Fisher (vMF) mixture model to this geometry using previously identified clean samples to capture semantic clusters. This geometric evidence is integrated with a semantic-label soft mapping mechanism to derive a distribution divergence between the label-free and annotated label-conditioned feature space, which robustly identifies noisy samples and updates the vMF mixture model with the newly separated clean dataset. Lastly, we employ an additional personalized noise absorption matrix on noisy labels to achieve robust optimization. Extensive experimental results demonstrate that method~significantly outperforms state-of-the-art methods for FL with data heterogeneity under diverse noisy clients scenarios.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 52 of its 76 references that are in the map. First posted on arXiv 20 Mar 2026.

Builds on

52 of 76 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2019Advances and Open Problems in Federated Learningcited by 3,021
  6. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  7. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  8. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  9. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  10. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  11. 2021Model-Contrastive Federated Learningcited by 762
  12. 2020Self-supervised Learning: Generative or Contrastivecited by 693
38 more
  1. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  2. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  3. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  4. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
  5. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  6. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  7. 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
  8. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  9. 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 108
  10. 2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
  11. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
  12. 2023FedExP: Speeding Up Federated Averaging via Extrapolationcited by 68
  13. 2023FedDisco: Federated Learning with Discrepancy-Aware Collaborationcited by 66
  14. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  15. 2019Self-Knowledge Distillation in Natural Language Processingcited by 60
  16. 2023FedFed: Feature Distillation against Data Heterogeneity in Federated Learningcited by 54
  17. 2022Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learningcited by 52
  18. 2017von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verificationcited by 45
  19. 2021Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterioncited by 36
  20. 2023FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneitycited by 33
  21. 2024An Aggregation-Free Federated Learning for Tackling Data Heterogeneitycited by 33
  22. 2022Towards Federated Learning against Noisy Labels via Local Self-Regularizationcited by 26
  23. 2021RoFL: Robustness of Secure Federated Learningcited by 23
  24. 2022When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Methodcited by 21
  25. 2023Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initializationcited by 21
  26. 2021Delving into Sample Loss Curve to Embrace Noisy and Imbalanced Datacited by 16
  27. 2023Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clientscited by 12
  28. 2022Communication-Efficient Robust Federated Learning with Noisy Labelscited by 11
  29. 2023Transferring Annotator- and Instance-dependent Transition Matrix for Learning from Crowdscited by 11
  30. 2023FedNoisy: Federated Noisy Label Learning Benchmarkcited by 11
  31. 2024Tackling Noisy Clients in Federated Learning with End-to-end Label Correctioncited by 11
  32. 2025Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learningcited by 11
  33. 2024FedFixer: Mitigating Heterogeneous Label Noise in Federated Learningcited by 8
  34. 2025FNBench: Benchmarking Robust Federated Learning against Noisy Labelscited by 6
  35. 2023Federated Skewed Label Learning with Logits Fusioncited by 5
  36. 2025FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learningcited by 4
  37. 2024Distribution-Aware Robust Learning from Long-Tailed Data with Noisy Labelscited by 2
  38. 2025FedPCA: Noise-Robust Fair Federated Learning via Performance-Capacity Analysiscited by 2

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.