mlsanityData to 7 Oct 2026

Trading Off Privacy, Utility and Efficiency in Federated Learning

arXiv 2209.00230 ↗First posted 1 Sep 2022cs.LG cs.CR cs.DCcited by 33

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables participating parties to collaboratively build a global model with boosted utility without disclosing private data information. Appropriate protection mechanisms have to be adopted to fulfill the opposing requirements in preserving textitprivacy and maintaining high model textitutility. In addition, it is a mandate for a federated learning system to achieve high textitefficiency in order to enable large-scale model training and deployment. We propose a unified federated learning framework that reconciles horizontal and vertical federated learning. Based on this framework, we formulate and quantify the trade-offs between privacy leakage, utility loss, and efficiency reduction, which leads us to the No-Free-Lunch (NFL) theorem for the federated learning system. NFL indicates that it is unrealistic to expect an FL algorithm to simultaneously provide excellent privacy, utility, and efficiency in certain scenarios. We then analyze the lower bounds for the privacy leakage, utility loss and efficiency reduction for several widely-adopted protection mechanisms including textitRandomization, textitHomomorphic Encryption, textitSecret Sharing and textitCompression. Our analysis could serve as a guide for selecting protection parameters to meet particular requirements.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 27 of its 62 references that are in the map. First posted on arXiv 1 Sep 2022.

Builds on

27 of 62 references.

References · 27

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  5. 2019Deep Leakage from Gradientscited by 1,004
  6. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  7. 2020The Future of Digital Health with Federated Learningcited by 625
  8. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  9. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  10. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  11. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 407
  12. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
15 more
  1. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  2. 2018Distributed learning of deep neural network over multiple agentscited by 277
  3. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  4. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 174
  5. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  6. 2021Label Leakage and Protection in Two-party Split Learningcited by 87
  7. 2018Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGDcited by 76
  8. 2020Breaking the Communication-Privacy-Accuracy Trilemmacited by 68
  9. 2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
  10. 2020Federated Doubly Stochastic Kernel Learning for Vertically Partitioned Datacited by 35
  11. 2021Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretabilitycited by 28
  12. 2021Fast Federated Learning by Balancing Communication Trade-Offscited by 18
  13. 2020Constraining Variational Inference with Geometric Jensen-Shannon Divergencecited by 17
  14. 2021Federated Deep Learning with Bayesian Privacycited by 13
  15. 2020Sharing Models or Coresets: A Study based on Membership Inference Attackcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 13; 2024: 10; 2025: 4; 2026: 4.

33 papers.

Sort:

By area:

  1. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 104
  2. 2023Federated Continual Learning via Knowledge Fusion: A Surveycited by 53
  3. 2024Advances and Open Challenges in Federated Foundation Modelscited by 33
  4. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  5. 2023A Survey for Federated Learning Evaluations: Goals and Measurescited by 16
  6. 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Surveycited by 14
  7. 2025FlexOlmo: Open Language Models for Flexible Data Usecited by 14
  8. 2023Optimizing Privacy, Utility and Efficiency in Constrained Multi-Objective Federated Learningcited by 12
  9. 2022A Framework for Evaluating Privacy-Utility Trade-off in Vertical Federated Learningcited by 10
  10. 2023FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscationcited by 9
  11. 2024FedProK: Trustworthy Federated Class-Incremental Learning via Prototypical Feature Knowledge Transfercited by 9
  12. 2023Towards Achieving Near-optimal Utility for Privacy-Preserving Federated Learning via Data Generation and Parameter Distortioncited by 6
21 more
  1. 2023Theoretically Principled Federated Learning for Balancing Privacy and Utilitycited by 6
  2. 2023A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learningcited by 6
  3. 2023Fake It Till Make It: Federated Learning with Consensus-Oriented Generationcited by 6
  4. 2024A Survey on Contribution Evaluation in Vertical Federated Learningcited by 5
  5. 2023Probably Approximately Correct Federated Learningcited by 4
  6. 2024HiFGL: A Hierarchical Framework for Cross-silo Cross-device Federated Graph Learningcited by 4
  7. 2025Towards Harnessing the Collaborative Power of Large and Small Models for Domain Taskscited by 4
  8. 2023Federated Learning Empowered by Generative Contentcited by 3
  9. 2023A Game-theoretic Framework for Privacy-preserving Federated Learningcited by 2
  10. 2023Automated discovery of trade-off between utility, privacy and fairness in machine learning modelscited by 2
  11. 2024NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQAcited by 2
  12. 2024Hyperparameter Optimization for SecureBoost via Constrained Multi-Objective Federated Learningcited by 1
  13. 2024Against Multifaceted Graph Heterogeneity via Asymmetric Federated Prompt Learningcited by 1
  14. 2024FedAdOb: Privacy-Preserving Federated Deep Learning with Adaptive Obfuscationcited by 0
  15. 2024Optimal Defenses Against Gradient Reconstruction Attackscited by 0
  16. 2025Harmonizing Generalization and Personalization in Ring-topology Decentralized Federated Learningcited by 0
  17. 2025A Survey of Personalized Federated Foundation Models for Privacy-Preserving Recommendationcited by 0
  18. 2026Balancing Privacy-Quality-Efficiency in Federated Learning through Round-Based Interleaving of Protection Techniquescited by 0
  19. 2026MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unificationcited by 0
  20. 2026Position: Artificial Intelligence Needs Meta Intelligence -- the Case for Metacognitive AIcited by 0
  21. 2026Privacy Leakage in Federated Learning in Radiology Reports: A Comparative Evaluation of Tokenizer-Driven Privacy Riskscited by 0