mlsanityData to 14 Oct 2026

Eliminating Domain Bias for Federated Learning in Representation Space

arXiv 2311.14975 ↗First posted 25 Nov 2023cs.LG cs.DCcited by 38

Not on the map. Why?

Abstract (arXiv)

Recently, federated learning (FL) is popular for its privacy-preserving and collaborative learning abilities. However, under statistically heterogeneous scenarios, we observe that biased data domains on clients cause a representation bias phenomenon and further degenerate generic representations during local training, i.e., the representation degeneration phenomenon. To address these issues, we propose a general framework Domain Bias Eliminator (DBE) for FL. Our theoretical analysis reveals that DBE can promote bi-directional knowledge transfer between server and client, as it reduces the domain discrepancy between server and client in representation space. Besides, extensive experiments on four datasets show that DBE can greatly improve existing FL methods in both generalization and personalization abilities. The DBE-equipped FL method can outperform ten state-of-the-art personalized FL methods by a large margin. Our code is public at https://github.com/TsingZ0/DBE.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 59 of its 95 references that are in the map. First posted on arXiv 25 Nov 2023.

Builds on

59 of 95 references.

References · 59

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2019Advances and Open Problems in Federated Learningcited by 3,046
  6. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  7. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
  8. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  9. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  10. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  11. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  12. 2016Bag of Tricks for Efficient Text Classificationcited by 876
38 more
  1. 2020A Primer in BERTology: What we know about how BERT workscited by 815
  2. 2021Model-Contrastive Federated Learningcited by 766
  3. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  4. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  5. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  6. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  7. 2019Federated Learning with Personalization Layerscited by 541
  8. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  9. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  10. 2021Towards Personalized Federated Learningcited by 464
  11. 2018On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transportcited by 426
  12. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 400
  13. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
  14. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 377
  15. 2020Adaptive Personalized Federated Learningcited by 358
  16. 2021True Few-Shot Learning with Language Modelscited by 344
  17. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  18. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 325
  19. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 252
  20. 2020Information-Theoretic Probing with Minimum Description Lengthcited by 232
  21. 2021Personalized Federated Learning using Hypernetworkscited by 212
  22. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  23. 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
  24. 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 182
  25. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  26. 2022Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learningcited by 172
  27. 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 155
  28. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 142
  29. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
  30. 2022FedALA: Adaptive Local Aggregation for Personalized Federated Learningcited by 122
  31. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 106
  32. 2017Network Representation Learning: A Surveycited by 101
  33. 2014Deep learning with Elastic Averaging SGDcited by 90
  34. 2021HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Imagescited by 64
  35. 2021Provably Secure Federated Learning against Malicious Clientscited by 63
  36. 2020An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guaranteecited by 62
  37. 2021Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learningcited by 53
  38. 2022Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillationcited by 45

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 12; 2025: 16; 2026: 9.

38 papers.

Sort:

By area:

  1. 2024Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Modelscited by 18
  2. 2023PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmarkcited by 17
  3. 2024An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learningcited by 17
  4. 2024FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preferencecited by 16
  5. 2024DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devicescited by 9
  6. 2025PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learningcited by 9
  7. 2025S2FGL: Spatial Spectral Federated Graph Learningcited by 7
  8. 2024Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuningcited by 6
  9. 2024Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradientscited by 3
  10. 2024Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformationcited by 2
  11. 2024FedAH: Aggregated Head for Personalized Federated Learningcited by 2
  12. 2025Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learningcited by 2
26 more
  1. 2025APFL: Analytic Personalized Federated Learning via Dual-Stream Least Squarescited by 2
  2. 2024Distributionally Robust Alignment for Medical Federated Vision-Language Pre-training Under Data Heterogeneitycited by 1
  3. 2024TPFL: A Trustworthy Personalized Federated Learning Framework via Subjective Logiccited by 1
  4. 2025Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypescited by 1
  5. 2025Robust Federated Learning with Global Sensitivity Estimation for Financial Risk Managementcited by 1
  6. 2025FedDyMem: Efficient Federated Learning with Dynamic Memory and Memory-Reduce for Unsupervised Image Anomaly Detectioncited by 1
  7. 2025Enhancing Federated Class-Incremental Learning via Spatial-Temporal Statistics Aggregationcited by 1
  8. 2025Improving Generalization in Heterogeneous Federated Continual Learning via Spatio-Temporal Gradient Matching with Prototypical Coresetcited by 1
  9. 2025FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learningcited by 1
  10. 2026FedCCA: Client-Centric Adaptation against Data Heterogeneity in Federated Learning on IoT Devicescited by 1
  11. 2026SubFLOT: Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transportcited by 1
  12. 2024FedLog: Personalized Federated Classification with Less Communication and More Flexibilitycited by 0
  13. 2024Adaptive Guidance for Local Training in Heterogeneous Federated Learningcited by 0
  14. 2025FedAPA: Server-side Gradient-Based Adaptive Personalized Aggregation for Federated Learning on Heterogeneous Datacited by 0
  15. 2025FedSCA: Federated Tuning with Similarity-guided Collaborative Aggregation for Heterogeneous Medical Image Segmentationcited by 0
  16. 2025FedEPA: Enhancing Personalization and Modality Alignment in Multimodal Federated Learningcited by 0
  17. 2025Whom to Trust? Adaptive Collaboration in Personalized Federated Learningcited by 0
  18. 2025Federated Learning in Offline and Online EMG Decoding: A Privacy and Performance Perspectivecited by 0
  19. 2025FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutionscited by 0
  20. 2026When the Server Steps In: Calibrated Updates for Fair Federated Learningcited by 0
  21. 2026Federated Balanced Learningcited by 0
  22. 2026FedRD: Reducing Divergences for Generalized Federated Learning via Heterogeneity-aware Parameter Guidancecited by 0
  23. 2026CoRe-Fed: Bridging Collaborative and Representation Fairness via Federated Embedding Distillationcited by 0
  24. 2026Federated Learning at the Forefront of Fairness: A Multifaceted Perspectivecited by 0
  25. 2026FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shiftcited by 0
  26. 2026HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learningcited by 0