mlsanityData to 7 Oct 2026

An Aggregation-Free Federated Learning for Tackling Data Heterogeneity

arXiv 2404.18962 ↗First posted 29 Apr 2024cs.CV cs.LGcited by 33

Not on the map. Why?

Abstract (arXiv)

The performance of Federated Learning (FL) hinges on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global model aggregated by the server from the previous training round. This process can cause client drift, especially with significant cross-client data heterogeneity, impacting model performance and convergence of the FL algorithm. To address these challenges, we introduce FedAF, a novel aggregation-free FL algorithm. In this framework, clients collaboratively learn condensed data by leveraging peer knowledge, the server subsequently trains the global model using the condensed data and soft labels received from the clients. FedAF inherently avoids the issue of client drift, enhances the quality of condensed data amid notable data heterogeneity, and improves the global model performance. Extensive numerical studies on several popular benchmark datasets show FedAF surpasses various state-of-the-art FL algorithms in handling label-skew and feature-skew data heterogeneity, leading to superior global model accuracy and faster convergence.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 31 of its 41 references that are in the map. First posted on arXiv 29 Apr 2024.

Builds on

31 of 41 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  5. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  6. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  7. 2018Federated Learning with Non-IID Datacited by 1,099
  8. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  9. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  10. 2021Model-Contrastive Federated Learningcited by 762
  11. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  12. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
19 more
  1. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 565
  2. 2021Federated Learning Based on Dynamic Regularizationcited by 555
  3. 2020Dataset Condensation with Gradient Matchingcited by 510
  4. 2022Dataset Distillation by Matching Training Trajectoriescited by 437
  5. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 380
  6. 2021Dataset Condensation with Distribution Matchingcited by 362
  7. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  8. 2021A Field Guide to Federated Optimizationcited by 312
  9. 2021Dataset Condensation with Differentiable Siamese Augmentationcited by 290
  10. 2018Dataset Distillationcited by 224
  11. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  12. 2020FedBE: Making Bayesian Model Ensemble Applicable to Federated Learningcited by 176
  13. 2022Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learningcited by 172
  14. 2022Privacy for Free: How does Dataset Condensation Help Privacy?cited by 119
  15. 2018Generative Modeling using the Sliced Wasserstein Distancecited by 108
  16. 2022FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learningcited by 65
  17. 2015Sliced Wasserstein Kernels for Probability Distributionscited by 64
  18. 2023Learning Federated Visual Prompt in Null Space for MRI Reconstructioncited by 40
  19. 2022Meta Knowledge Condensation for Federated Learningcited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 18; 2026: 5.

33 papers.

Sort:

By area:

  1. 2024LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinementcited by 37
  2. 2025The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutionscited by 24
  3. 2024Generative Dataset Distillation Based on Diffusion Modelcited by 13
  4. 2025TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendationcited by 13
  5. 2025FedALT: Federated Fine-Tuning through Adaptive Local Training with Rest-of-World LoRAcited by 13
  6. 2025FedRSClip: Federated Learning for Remote Sensing Scene Classification Using Vision-Language Modelscited by 11
  7. 2025Subgraph Federated Learning for Local Generalizationcited by 6
  8. 2024Going Beyond Feature Similarity: Effective Dataset Distillation based on Class-Aware Conditional Mutual Informationcited by 4
  9. 2025FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learningcited by 4
  10. 2024Dataset Distillation from First Principles: Integrating Core Information Extraction and Purposeful Learningcited by 3
  11. 2025Maximizing Uncertainty for Federated learning via Bayesian Optimisation-based Model Poisoningcited by 3
  12. 2025AFCL: Analytic Federated Continual Learning for Spatio-Temporal Invariance of Non-IID Datacited by 3
21 more
  1. 2025FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learningcited by 3
  2. 2025Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practicecited by 3
  3. 2024SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustmentscited by 2
  4. 2024Dataset Distillation-based Hybrid Federated Learning on Non-IID Datacited by 2
  5. 2024Tackling Data Heterogeneity in Federated Time Series Forecastingcited by 2
  6. 2024Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networkscited by 2
  7. 2025Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distributed Environmentscited by 2
  8. 2024Federated Cross-Training Learners for Robust Generalization under Data Heterogeneitycited by 1
  9. 2024Recent Advances in Federated Learning Driven Large Language Models: A Survey on Architecture, Performance, and Securitycited by 1
  10. 2025Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypescited by 1
  11. 2025FedDiverse: Tackling Data Heterogeneity in Federated Learning with Diversity-Driven Client Selectioncited by 1
  12. 2025Distribution-Aware Mobility-Assisted Decentralized Federated Learningcited by 1
  13. 2025High-Energy Concentration for Federated Learning in Frequency Domaincited by 1
  14. 2025Adaptive Prototype Knowledge Transfer for Federated Learning with Mixed Modalities and Heterogeneous Taskscited by 0
  15. 2025On optimal solutions of classical and sliced Wasserstein GANs with non-Gaussian datacited by 0
  16. 2025Mobility-Assisted Decentralized Federated Learning: Convergence Analysis and A Data-Driven Approachcited by 0
  17. 2026Foreground-Aware Dataset Distillation via Dynamic Patch Selectioncited by 0
  18. 2026HiLoRA: Hierarchical Low-Rank Adaptation for Personalized Federated Learningcited by 0
  19. 2026Domain-Skewed Federated Learning with Feature Decoupling and Calibrationcited by 0
  20. 2026FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clientscited by 0
  21. 2026ReSCENE: Server-Side Replay for Structural Mitigation of Catastrophic Forgetting in Federated Continual Learningcited by 0