mlsanityData to 7 Oct 2026

Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features

arXiv 2204.13399 ↗First posted 28 Apr 2022cs.LGcited by 63

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) provides a privacy-preserving solution for distributed machine learning tasks. One challenging problem that severely damages the performance of FL models is the co-occurrence of data heterogeneity and long-tail distribution, which frequently appears in real FL applications. In this paper, we reveal an intriguing fact that the biased classifier is the primary factor leading to the poor performance of the global model. Motivated by the above finding, we propose a novel and privacy-preserving FL method for heterogeneous and long-tailed data via Classifier Re-training with Federated Features (CReFF). The classifier re-trained on federated features can produce comparable performance as the one re-trained on real data in a privacy-preserving manner without information leakage of local data or class distribution. Experiments on several benchmark datasets show that the proposed CReFF is an effective solution to obtain a promising FL model under heterogeneous and long-tailed data. Comparative results with the state-of-the-art FL methods also validate the superiority of CReFF. Our code is available at https://github.com/shangxinyi/CReFF-FL.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). Builds on 22 of its 25 references that are in the map. First posted on arXiv 28 Apr 2022.

Builds on

22 of 25 references.

References · 22

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  5. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  6. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  7. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  8. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  9. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  10. 2020Dataset Condensation with Gradient Matchingcited by 510
  11. 2021Deep Long-Tailed Learning: A Surveycited by 416
  12. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 270
10 more
  1. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  2. 2020FedBE: Making Bayesian Model Ensemble Applicable to Federated Learningcited by 176
  3. 2020Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classificationcited by 175
  4. 2020M2m: Imbalanced Classification via Major-to-minor Translationcited by 134
  5. 2021FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentationcited by 76
  6. 2020Federated learning with class imbalance reductioncited by 52
  7. 2020Fed-Focal Loss for imbalanced data classification in Federated Learningcited by 26
  8. 2021FedSpeech: Federated Text-to-Speech with Continual Learningcited by 16
  9. 2019"The Squawk Bot": Joint Learning of Time Series and Text Data Modalities for Automated Financial Information Filteringcited by 13
  10. 2021Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learningcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 16; 2024: 23; 2025: 14; 2026: 7.

63 papers.

Sort:

By area:

  1. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
  2. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  3. 2022Tackling Data Heterogeneity in Federated Learning with Class Prototypescited by 66
  4. 2023No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifiercited by 55
  5. 2023Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Datacited by 35
  6. 2023FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneitycited by 33
  7. 2024A Systematic Review on Long-Tailed Learningcited by 27
  8. 2024PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learningcited by 19
  9. 2025FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectorscited by 19
  10. 2022FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image Classificationcited by 18
  11. 2023Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancercited by 17
  12. 2024Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Datacited by 14
38 more
  1. 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Surveycited by 14
  2. 2024FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Datacited by 10
  3. 2024Accelerating Heterogeneous Federated Learning with Closed-form Classifierscited by 10
  4. 2023CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Datacited by 9
  5. 2024Enable the Right to be Forgotten with Federated Client Unlearning in Medical Imagingcited by 9
  6. 2025Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Datacited by 9
  7. 2022Towards Federated Long-Tailed Learningcited by 7
  8. 2025S2FGL: Spatial Spectral Federated Graph Learningcited by 7
  9. 2023Dynamic Heterogeneous Federated Learning with Multi-Level Prototypescited by 6
  10. 2025You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Datacited by 5
  11. 2023FCA: Taming Long-tailed Federated Medical Image Classification by Classifier Anchoringcited by 4
  12. 2023Federated Model Aggregation via Self-Supervised Priors for Highly Imbalanced Medical Image Classificationcited by 4
  13. 2024FedLF: Adaptive Logit Adjustment and Feature Optimization in Federated Long-Tailed Learningcited by 4
  14. 2023Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learningcited by 3
  15. 2023FedBug: A Bottom-Up Gradual Unfreezing Framework for Federated Learningcited by 3
  16. 2024Bridging Data Islands: Geographic Heterogeneity-Aware Federated Learning for Collaborative Remote Sensing Semantic Segmentationcited by 3
  17. 2024MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learningcited by 3
  18. 2024FedReMa: Improving Personalized Federated Learning via Leveraging the Most Relevant Clientscited by 3
  19. 2024SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustmentscited by 2
  20. 2024Addressing Skewed Heterogeneity via Federated Prototype Rectification with Personalizationcited by 2
  21. 2025Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distributed Environmentscited by 2
  22. 2024Decoupled Federated Learning on Long-Tailed and Non-IID data with Feature Statisticscited by 1
  23. 2024Federated Cross-Training Learners for Robust Generalization under Data Heterogeneitycited by 1
  24. 2024Federated Active Learning Framework for Efficient Annotation Strategy in Skin-lesion Classificationcited by 1
  25. 2024Personalized Federated Learning on Heterogeneous and Long-Tailed Data via Expert Collaborative Learningcited by 1
  26. 2024Mitigating Malicious Attacks in Federated Learning via Confidence-aware Defensecited by 1
  27. 2025CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Modelcited by 1
  28. 2025FedBKD: Distilled Federated Learning to Embrace Gerneralization and Personalization on Non-IID Datacited by 1
  29. 2025Operator-Theoretic Framework for Gradient-Free Federated Learningcited by 1
  30. 2026Fine-Tuning Impairs the Balancedness of Foundation Models in Long-tailed Personalized Federated Learningcited by 1
  31. 2026Condensing Large-Scale Datasets Directly with Minimal Information Losscited by 1
  32. 2023A Unified Momentum-based Paradigm of Decentralized SGD for Non-Convex Models and Heterogeneous Datacited by 0
  33. 2023FedDCT: A Dynamic Cross-Tier Federated Learning Framework in Wireless Networkscited by 0
  34. 2023Tackling Computational Heterogeneity in FL: A Few Theoretical Insightscited by 0
  35. 2023Personalized Federated Learning via ADMM with Moreau Envelopecited by 0
  36. 2024DA-PFL: Dynamic Affinity Aggregation for Personalized Federated Learningcited by 0
  37. 2024Non-parametric regularization for class imbalance federated medical image classificationcited by 0
  38. 2024On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairnesscited by 0

50 most cited of 63 All 63 (JSON)