mlsanityData to 7 Oct 2026

A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency

arXiv 2307.10655 ↗First posted 20 Jul 2023cs.LG cs.CRcited by 21

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) has emerged as a secure paradigm for collaborative training among clients. Without data centralization, FL allows clients to share local information in a privacy-preserving manner. This approach has gained considerable attention, promoting numerous surveys to summarize the related works. However, the majority of these surveys concentrate on FL methods that share model parameters during the training process, while overlooking the possibility of sharing local information in other forms. In this paper, we present a systematic survey from a new perspective of what to share in FL, with an emphasis on the model utility, privacy leakage, and communication efficiency. First, we present a new taxonomy of FL methods in terms of three sharing methods, which respectively share model, synthetic data, and knowledge. Second, we analyze the vulnerability of different sharing methods to privacy attacks and review the defense mechanisms. Third, we conduct extensive experiments to compare the learning performance and communication overhead of various sharing methods in FL. Besides, we assess the potential privacy leakage through model inversion and membership inference attacks, while comparing the effectiveness of various defense approaches. Finally, we identify future research directions and conclude the survey.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 140 of its 226 references that are in the map. First posted on arXiv 20 Jul 2023.

Builds on

140 of 226 references.

References · 140

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2019Advances and Open Problems in Federated Learningcited by 3,021
  7. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  8. 2016Deep Learning with Differential Privacycited by 2,682
  9. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  10. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  11. 2020Knowledge Distillation: A Surveycited by 1,578
  12. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
38 more
  1. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  2. 2018Federated Learning with Non-IID Datacited by 1,099
  3. 2019Deep Leakage from Gradientscited by 1,004
  4. 2018LEAF: A Benchmark for Federated Settingscited by 780
  5. 2021Model-Contrastive Federated Learningcited by 762
  6. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  7. 2017Renyi Differential Privacycited by 643
  8. 2017Generative Adversarial Networks: An Overviewcited by 588
  9. 2020Federated Learning with Matched Averagingcited by 564
  10. 2021Federated Learning Based on Dynamic Regularizationcited by 555
  11. 2020Dataset Condensation with Gradient Matchingcited by 510
  12. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  13. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  14. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  15. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
  16. 2019Federated Machine Learning: Concept and Applicationscited by 409
  17. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 407
  18. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
  19. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 380
  20. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 375
  21. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
  22. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  23. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
  24. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  25. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  26. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  27. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 334
  28. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  29. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  30. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  31. 2021The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networkscited by 285
  32. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  33. 2018Scalable Private Learning with PATEcited by 266
  34. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 265
  35. 2018Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Datacited by 242
  36. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  37. 2018Differentially Private Generative Adversarial Networkcited by 235
  38. 2018Dataset Distillationcited by 224

50 most cited of 140 All 140 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 8; 2025: 5; 2026: 2.

21 papers.

Sort:

  1. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  2. 2024WirelessLLM: Empowering Large Language Models Towards Wireless Intelligencecited by 43
  3. 2023Feature Matching Data Synthesis for Non-IID Federated Learningcited by 13
  4. 2023FedCiR: Client-Invariant Representation Learning for Federated Non-IID Featurescited by 12
  5. 2024One-shot Federated Learning via Synthetic Distiller-Distillate Communicationcited by 12
  6. 2024A Systematic Review of Federated Generative Modelscited by 5
  7. 2023Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learningcited by 4
  8. 2023Mode Connectivity and Data Heterogeneity of Federated Learningcited by 3
  9. 2024CCFC: Bridging Federated Clustering and Contrastive Learningcited by 3
  10. 2024An Empirical Study on Large Language Models in Accuracy and Robustness under Chinese Industrial Scenarioscited by 3
  11. 2024Federated Prompt-based Decision Transformer for Customized VR Services in Mobile Edge Computing Systemcited by 2
  12. 2024Federated Learning for Blind Image Super-Resolutioncited by 2
9 more
  1. 2025Federated Learning from Molecules to Processes: A Perspectivecited by 2
  2. 2024A Federated Online Restless Bandit Framework for Cooperative Resource Allocationcited by 1
  3. 2026Decentralized Federated Learning With Energy Harvesting Devicescited by 1
  4. 2023Feature Norm Regularized Federated Learning: Transforming Skewed Distributions into Global Insightscited by 0
  5. 2025ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoningcited by 0
  6. 2025Towards a Small Language Model Lifecycle Frameworkcited by 0
  7. 2025Federated Spatiotemporal Graph Learning for Passive Attack Detection in Smart Gridscited by 0
  8. 2025FedPF: Accurate Target Privacy Preserving Federated Learning Balancing Fairness and Utilitycited by 0
  9. 2026Quantization in Federated Learning: Methods, Challenges and Future Directionscited by 0