mlsanityData to 14 Oct 2026

Feature Matching Data Synthesis for Non-IID Federated Learning

arXiv 2308.04761 ↗First posted 9 Aug 2023cs.LG cs.AI cs.DCcited by 13

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) has emerged as a privacy-preserving paradigm that trains neural networks on edge devices without collecting data at a central server. However, FL encounters an inherent challenge in dealing with non-independent and identically distributed (non-IID) data among devices. To address this challenge, this paper proposes a hard feature matching data synthesis (HFMDS) method to share auxiliary data besides local models. Specifically, synthetic data are generated by learning the essential class-relevant features of real samples and discarding the redundant features, which helps to effectively tackle the non-IID issue. For better privacy preservation, we propose a hard feature augmentation method to transfer real features towards the decision boundary, with which the synthetic data not only improve the model generalization but also erase the information of real features. By integrating the proposed HFMDS method with FL, we present a novel FL framework with data augmentation to relieve data heterogeneity. The theoretical analysis highlights the effectiveness of our proposed data synthesis method in solving the non-IID challenge. Simulation results further demonstrate that our proposed HFMDS-FL algorithm outperforms the baselines in terms of accuracy, privacy preservation, and computational cost on various benchmark datasets.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 44 of its 62 references that are in the map. First posted on arXiv 9 Aug 2023.

Builds on

44 of 62 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2022Generative Adversarial Networkscited by 5,627
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  6. 2019Advances and Open Problems in Federated Learningcited by 3,046
  7. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  8. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  9. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  10. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  11. 2018Federated Learning with Non-IID Datacited by 1,108
  12. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
32 more
  1. 2021Model-Contrastive Federated Learningcited by 766
  2. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  3. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  4. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  5. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  6. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 423
  7. 2014Understanding Deep Image Representations by Inverting Themcited by 403
  8. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
  9. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  10. 2015Understanding Neural Networks Through Deep Visualizationcited by 334
  11. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  12. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  13. 2022Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformercited by 212
  14. 2016Synthesizing the preferred inputs for neurons in neural networks via deep generator networkscited by 181
  15. 2022Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learningcited by 172
  16. 2021Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learningcited by 131
  17. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
  18. 2021Towards Fair Federated Learning with Zero-Shot Data Augmentationcited by 64
  19. 2022FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learningcited by 64
  20. 2020XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learningcited by 58
  21. 2022Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learningcited by 52
  22. 2019Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Datacited by 38
  23. 2020Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixupcited by 29
  24. 2022Acceleration of Federated Learning with Alleviated Forgetting in Local Trainingcited by 29
  25. 2021IMAGINE: Image Synthesis by Image-Guided Model Inversioncited by 25
  26. 2022Federated Learning with GAN-based Data Synthesis for Non-IID Clientscited by 25
  27. 2023Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teachercited by 25
  28. 2021FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumoniacited by 22
  29. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  30. 2021Federated Learning for COVID-19 Detection with Generative Adversarial Networks in Edge Cloud Computingcited by 18
  31. 2020FedCD: Improving Performance in non-IID Federated Learningcited by 13
  32. 2022DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples Discriminationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 5; 2026: 4.

13 papers.

Sort:

  1. 2023FedCiR: Client-Invariant Representation Learning for Federated Non-IID Featurescited by 12
  2. 2024FedRFQ: Prototype-Based Federated Learning with Reduced Redundancy, Minimal Failure, and Enhanced Qualitycited by 5
  3. 2024Federated and Transfer Learning for Cancer Detection Based on Image Analysiscited by 3
  4. 2024IMFL-AIGC: Incentive Mechanism Design for Federated Learning Empowered by Artificial Intelligence Generated Contentcited by 3
  5. 2025FedDyMem: Efficient Federated Learning with Dynamic Memory and Memory-Reduce for Unsupervised Image Anomaly Detectioncited by 1
  6. 2025Adaptive Federated Distillation for Multi-Domain Non-IID Textual Datacited by 1
  7. 2026GFPL: Generative Federated Prototype Learning for Resource-Constrained and Data-Imbalanced Vision Taskcited by 1
  8. 2025Robust Federated Learning in Unreliable Wireless Networks: A Client Selection Approachcited by 0
  9. 2025AIGC-assisted Federated Learning for Edge Intelligence: Architecture Design, Research Challenges and Future Directionscited by 0
  10. 2025Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Samplingcited by 0
  11. 2026A Multi-Prototype-Guided Federated Knowledge Distillation Approach in AI-RAN Enabled Multi-Access Edge Computing Systemcited by 0
  12. 2026From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learningcited by 0
1 more
  1. 2026Joint Optimization for Federated Learning and Transmission over Unreliable Wireless Networks with Heterogeneous Datacited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Synthetic Data Aided Federated Learning Using Foundation Models
  2. 2025FedBKD: Distilled Federated Learning to Embrace Gerneralization and Personalization on Non-IID Data
  3. 2023FedFed: Feature Distillation against Data Heterogeneity in Federated Learning
  4. 2024Stable Diffusion-based Data Augmentation for Federated Learning with Non-IID Data
  5. 2024FedDW: Distilling Weights through Consistency Optimization in Heterogeneous Federated Learning
  6. 2025Diffusion Model-Based Data Synthesis Aided Federated Semi-Supervised Learning
  7. 2026Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy
  8. 2022sqSGD: Locally Private and Communication Efficient Federated Learning