mlsanityData to 7 Oct 2026

Towards Fair Federated Learning with Zero-Shot Data Augmentation

arXiv 2104.13417 ↗First posted 27 Apr 2021cs.CV cs.LG stat.MLcited by 64

Not on the map. Why?

Abstract (arXiv)

Federated learning has emerged as an important distributed learning paradigm, where a server aggregates a global model from many client-trained models while having no access to the client data. Although it is recognized that statistical heterogeneity of the client local data yields slower global model convergence, it is less commonly recognized that it also yields a biased federated global model with a high variance of accuracy across clients. In this work, we aim to provide federated learning schemes with improved fairness. To tackle this challenge, we propose a novel federated learning system that employs zero-shot data augmentation on under-represented data to mitigate statistical heterogeneity and encourage more uniform accuracy performance across clients in federated networks. We study two variants of this scheme, Fed-ZDAC (federated learning with zero-shot data augmentation at the clients) and Fed-ZDAS (federated learning with zero-shot data augmentation at the server). Empirical results on a suite of datasets demonstrate the effectiveness of our methods on simultaneously improving the test accuracy and fairness.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). Builds on 30 of its 43 references that are in the map. First posted on arXiv 27 Apr 2021.

Builds on

30 of 43 references.

References · 30

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  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. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  7. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  8. 2017Continual Learning with Deep Generative Replaycited by 1,152
  9. 2018Federated Learning with Non-IID Datacited by 1,099
  10. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  11. 2017Federated Multi-Task Learningcited by 669
  12. 2019Federated Learning with Personalization Layerscited by 533
18 more
  1. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  2. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  3. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 419
  4. 2019Fair Resource Allocation in Federated Learningcited by 389
  5. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 265
  6. 2018Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Datacited by 242
  7. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  8. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  9. 2019Overcoming Forgetting in Federated Learning on Non-IID Datacited by 120
  10. 2019Variational Federated Multi-Task Learningcited by 69
  11. 2018Universal Neural Machine Translation for Extremely Low Resource Languagescited by 66
  12. 2020MixKD: Towards Efficient Distillation of Large-scale Language Modelscited by 65
  13. 2019On Safeguarding Privacy and Security in the Framework of Federated Learningcited by 55
  14. 2020Federated Learning via Synthetic Datacited by 53
  15. 2020Analysis of Gender Inequality In Face Recognition Accuracycited by 47
  16. 2020Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentationcited by 45
  17. 2019Does Face Recognition Accuracy Get Better With Age? Deep Face Matchers Say Nocited by 16
  18. 2020WAFFLe: Weight Anonymized Factorization for Federated Learningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 15; 2023: 21; 2024: 14; 2025: 10; 2026: 2.

64 papers.

Sort:

By area:

  1. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  2. 2023Towards Building the Federated GPT: Federated Instruction Tuningcited by 184
  3. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  4. 2023FedFed: Feature Distillation against Data Heterogeneity in Federated Learningcited by 54
  5. 2022Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learningcited by 52
  6. 2022No One Left Behind: Inclusive Federated Learning over Heterogeneous Devicescited by 36
  7. 2023Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Datacited by 35
  8. 2022Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reductioncited by 32
  9. 2022Architecture Agnostic Federated Learning for Neural Networkscited by 30
  10. 2022Acceleration of Federated Learning with Alleviated Forgetting in Local Trainingcited by 29
  11. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  12. 2023Federated Domain Generalization: A Surveycited by 25
38 more
  1. 2022FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentationcited by 24
  2. 2022Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarkscited by 24
  3. 2022DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharingcited by 17
  4. 2022Federated Self-supervised Learning for Heterogeneous Clientscited by 16
  5. 2023Visual Prompt Based Personalized Federated Learningcited by 16
  6. 2024FedImpro: Measuring and Improving Client Update in Federated Learningcited by 15
  7. 2021Federated Learning from Small Datasetscited by 14
  8. 2023Feature Matching Data Synthesis for Non-IID Federated Learningcited by 13
  9. 2022Federated Learning in Non-IID Settings Aided by Differentially Private Synthetic Datacited by 12
  10. 2023A Survey on Class Imbalance in Federated Learningcited by 12
  11. 2023Bias Propagation in Federated Learningcited by 12
  12. 2024Advances in Robust Federated Learning: A Survey with Heterogeneity Considerationscited by 12
  13. 2024FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusioncited by 11
  14. 2025Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learningcited by 11
  15. 2023Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sourcescited by 10
  16. 2023Federated Recommendation with Additive Personalizationcited by 9
  17. 2022Towards Multi-Objective Statistically Fair Federated Learningcited by 8
  18. 2024A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applicationscited by 8
  19. 2024Federated Unlearning: a Perspective of Stability and Fairnesscited by 7
  20. 2023Fake It Till Make It: Federated Learning with Consensus-Oriented Generationcited by 6
  21. 2024CAR-MFL: Cross-Modal Augmentation by Retrieval for Multimodal Federated Learning with Missing Modalitiescited by 5
  22. 2022StatMix: Data augmentation method that relies on image statistics in federated learningcited by 4
  23. 2022Federated Zero-Shot Learning for Visual Recognitioncited by 4
  24. 2023PS-FedGAN: An Efficient Federated Learning Framework Based on Partially Shared Generative Adversarial Networks For Data Privacycited by 4
  25. 2023Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learningcited by 4
  26. 2023Federated Learning for 6G: Paradigms, Taxonomy, Recent Advances and Insightscited by 4
  27. 2024FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learningcited by 4
  28. 2023Towards Open Federated Learning Platforms: Survey and Vision from Technical and Legal Perspectivescited by 3
  29. 2023PFL-GAN: When Client Heterogeneity Meets Generative Models in Personalized Federated Learningcited by 3
  30. 2024ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Modelscited by 3
  31. 2024Synthetic Data Aided Federated Learning Using Foundation Modelscited by 3
  32. 2024MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learningcited by 3
  33. 2025FedSC: Federated Learning with Semantic-Aware Collaborationcited by 3
  34. 2025Distributed Zero-Shot Learning for Visual Recognitioncited by 3
  35. 2022Absolute Zero-Shot Learningcited by 2
  36. 2023Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learningcited by 2
  37. 2023TrojFair: Trojan Fairness Attackscited by 2
  38. 2024Data-Algorithm-Architecture Co-Optimization for Fair Neural Networks on Skin Lesion Datasetcited by 2

50 most cited of 64 All 64 (JSON)