mlsanityData to 14 Oct 2026

WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning

arXiv 2607.06616 ↗First posted 7 Jul 2026cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Label skew in federated learning (FL) causes client drift and degrades global accuracy. Synthetic data augmentation can reduce this imbalance; however, full class balancing requires substantial computation cost. We propose FedEAS, a policy that assigns each client an entropy-adaptive per-class generation budget computed from its local label distribution. The budget jointly decides how much each client generates and WHERE the samples go. Accordingly, the total generation budget follows from the per-client budgets rather than being fixed in advance. FedEAS recovers most of the accuracy gain of full class balancing while reducing the generation budget by 94.1%. At the same total generation budget, it outperforms Uniform allocation by up to 18.82% across CIFAR-10 and CIFAR-100.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 52 of its 61 references that are in the map. First posted on arXiv 7 Jul 2026.

Builds on

52 of 61 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  7. 2022Classifier-Free Diffusion Guidancecited by 5,847
  8. 2022Generative Adversarial Networkscited by 5,627
  9. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  10. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  11. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  12. 2019Advances and Open Problems in Federated Learningcited by 3,046
38 more
  1. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  2. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  3. 2016Deep Learning with Differential Privacycited by 2,728
  4. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  5. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  6. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  7. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  8. 2018Federated Learning with Non-IID Datacited by 1,108
  9. 2020Adaptive Federated Optimizationcited by 1,046
  10. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  11. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  12. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  13. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  14. 2021Model-Contrastive Federated Learningcited by 766
  15. 2023Adversarial Diffusion Distillationcited by 759
  16. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  17. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  18. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  19. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  20. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  21. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
  22. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 327
  23. 2022Is synthetic data from generative models ready for image recognition?cited by 320
  24. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 312
  25. 2023Effective Data Augmentation With Diffusion Modelscited by 283
  26. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  27. 2023StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learnerscited by 177
  28. 2022Fake it till you make it: Learning transferable representations from synthetic ImageNet clonescited by 172
  29. 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 109
  30. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
  31. 2023Differentially Private Diffusion Models Generate Useful Synthetic Imagescited by 86
  32. 2023No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifiercited by 55
  33. 2022On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Datacited by 38
  34. 2023FedFA: Federated Feature Augmentationcited by 22
  35. 2023A Simple Data Augmentation for Feature Distribution Skewed Federated Learningcited by 17
  36. 2023Exploiting Label Skews in Federated Learning with Model Concatenationcited by 14
  37. 2023Filling the Missing: Exploring Generative AI for Enhanced Federated Learning over Heterogeneous Mobile Edge Devicescited by 13
  38. 2024Stable Diffusion-based Data Augmentation for Federated Learning with Non-IID Datacited by 11

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.