mlsanityData to 7 Oct 2026

Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains

arXiv 2403.09048 ↗First posted 14 Mar 2024cs.LG cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) allows collaborative machine learning training without sharing private data. While most FL methods assume identical data domains across clients, real-world scenarios often involve heterogeneous data domains. Federated Prototype Learning (FedPL) addresses this issue, using mean feature vectors as prototypes to enhance model generalization. However, existing FedPL methods create the same number of prototypes for each client, leading to cross-domain performance gaps and disparities for clients with varied data distributions. To mitigate cross-domain feature representation variance, we introduce FedPLVM, which establishes variance-aware dual-level prototypes clustering and employs a novel α-sparsity prototype loss. The dual-level prototypes clustering strategy creates local clustered prototypes based on private data features, then performs global prototypes clustering to reduce communication complexity and preserve local data privacy. The α-sparsity prototype loss aligns samples from underrepresented domains, enhancing intra-class similarity and reducing inter-class similarity. Evaluations on Digit-5, Office-10, and DomainNet datasets demonstrate our method's superiority over existing approaches.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 35 of its 46 references that are in the map. First posted on arXiv 14 Mar 2024.

Builds on

35 of 46 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  6. 2020Supervised Contrastive Learningcited by 2,803
  7. 2016Deep Learning with Differential Privacycited by 2,682
  8. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  9. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  10. 2018Federated Learning with Non-IID Datacited by 1,099
  11. 2021Model-Contrastive Federated Learningcited by 762
  12. 2021Federated Learning Based on Dynamic Regularizationcited by 555
23 more
  1. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 415
  2. 2020Understanding the Behaviour of Contrastive Losscited by 397
  3. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  4. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  5. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  6. 2019R'enyi Differential Privacy of the Sampled Gaussian Mechanismcited by 199
  7. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 141
  8. 2020The Discrete Gaussian for Differential Privacycited by 134
  9. 2019Overcoming Forgetting in Federated Learning on Non-IID Datacited by 120
  10. 2019Efficient Parameter-free Clustering Using First Neighbor Relationscited by 96
  11. 2020Federated Unsupervised Representation Learningcited by 92
  12. 2021FedProc: Prototypical Contrastive Federated Learning on Non-IID datacited by 80
  13. 2022Tackling Data Heterogeneity in Federated Learning with Class Prototypescited by 66
  14. 2021A Prototype-Oriented Framework for Unsupervised Domain Adaptationcited by 62
  15. 2022FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learningcited by 62
  16. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  17. 2021Federated Learning with Domain Generalizationcited by 41
  18. 2020Robust Federated Learning with Noisy Labelscited by 40
  19. 2021Personalized Federated Learning with Adaptive Batchnorm for Healthcarecited by 26
  20. 2023FedFA: Federated Feature Augmentationcited by 22
  21. 2020A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergencescited by 21
  22. 2015Prototypical Priors: From Improving Classification to Zero-Shot Learningcited by 14
  23. 2023Federated Learning with Instance-Dependent Noisy Labelcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 15; 2026: 8.

27 papers.

Sort:

By area:

  1. 2024LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinementcited by 37
  2. 2025FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averagingcited by 25
  3. 2025FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Modelscited by 15
  4. 2025FedALT: Federated Fine-Tuning through Adaptive Local Training with Rest-of-World LoRAcited by 13
  5. 2025Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuningcited by 5
  6. 2024Prioritizing Modalities: Flexible Importance Scheduling in Federated Multimodal Learningcited by 4
  7. 2025FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learningcited by 4
  8. 2025FedEL: Federated Elastic Learning for Heterogeneous Devicescited by 3
  9. 2025Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learningcited by 2
  10. 2025FedPall: Prototype-based Adversarial and Collaborative Learning for Federated Learning with Feature Driftcited by 2
  11. 2025C^2Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learningcited by 2
  12. 2025Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Segmentationcited by 2
15 more
  1. 2026FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuningcited by 2
  2. 2024Modality Alignment Meets Federated Broadcastingcited by 1
  3. 2025Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypescited by 1
  4. 2025FedORGP: Guiding Heterogeneous Federated Learning with Orthogonality Regularization on Global Prototypescited by 1
  5. 2025FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learningcited by 1
  6. 2024An Enhanced Federated Prototype Learning Method under Domain Shiftcited by 0
  7. 2025FEDEXCHANGE: Bridging the Domain Gap in Federated Object Detection for Freecited by 0
  8. 2025BAPFL: Exploring Backdoor Attacks Against Prototype-based Federated Learningcited by 0
  9. 2026A Multi-Prototype-Guided Federated Knowledge Distillation Approach in AI-RAN Enabled Multi-Access Edge Computing Systemcited by 0
  10. 2026Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expressioncited by 0
  11. 2026FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shiftcited by 0
  12. 2026From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learningcited by 0
  13. 2026FedProIn: Mitigating Client Drift for Learnable Prototypes in Federated Medical Imagingcited by 0
  14. 2026FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Driftcited by 0
  15. 2026When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimationcited by 0