mlsanityData to 7 Oct 2026

Privacy Amplification for Federated Learning via User Sampling and Wireless Aggregation

arXiv 2103.01953 ↗First posted 2 Mar 2021cs.IT cs.CR cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

In this paper, we study the problem of federated learning over a wireless channel with user sampling, modeled by a Gaussian multiple access channel, subject to central and local differential privacy (DP/LDP) constraints. It has been shown that the superposition nature of the wireless channel provides a dual benefit of bandwidth efficient gradient aggregation, in conjunction with strong DP guarantees for the users. Specifically, the central DP privacy leakage has been shown to scale as O(1/K1/2), where K is the number of users. It has also been shown that user sampling coupled with orthogonal transmission can enhance the central DP privacy leakage with the same scaling behavior. In this work, we show that, by join incorporating both wireless aggregation and user sampling, one can obtain even stronger privacy guarantees. We propose a private wireless gradient aggregation scheme, which relies on independently randomized participation decisions by each user. The central DP leakage of our proposed scheme scales as O(1/K3/4). In addition, we show that LDP is also boosted by user sampling. We also present analysis for the convergence rate of the proposed scheme and study the tradeoffs between wireless resources, convergence, and privacy theoretically and empirically for two scenarios when the number of sampled participants are (a) known, or (b) unknown at the parameter server.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 27 of its 37 references that are in the map. First posted on arXiv 2 Mar 2021.

Builds on

27 of 37 references.

References · 27

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  4. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  5. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  6. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  7. 2013The Composition Theorem for Differential Privacycited by 290
  8. 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 237
  9. 2018Federated Learning via Over-the-Air Computationcited by 215
  10. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
  11. 2019Federated Learning over Wireless Fading Channelscited by 178
  12. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 163
15 more
  1. 2018cpSGD: Communication-efficient and differentially-private distributed SGDcited by 157
  2. 2019Hierarchical Federated Learning Across Heterogeneous Cellular Networkscited by 98
  3. 2019Federated Learning for Edge Networks: Resource Optimization and Incentive Mechanismcited by 75
  4. 2020Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Controlcited by 62
  5. 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 61
  6. 2019Federated Learning with Bayesian Differential Privacycited by 60
  7. 2020Wireless Federated Learning with Local Differential Privacycited by 50
  8. 2019Differential Privacy-enabled Federated Learning for Sensitive Health Datacited by 44
  9. 2019Energy-Efficient Radio Resource Allocation for Federated Edge Learningcited by 39
  10. 2020Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluationcited by 39
  11. 2020Privacy Amplification via Random Check-Inscited by 39
  12. 2018Stochastic Gradient Descent with Biased but Consistent Gradient Estimatorscited by 18
  13. 2020Private Wireless Federated Learning with Anonymous Over-the-Air Computationcited by 16
  14. 2018Local Differential Privacy for Evolving Datacited by 6
  15. 2020Efficient Federated Learning over Multiple Access Channel with Differential Privacy Constraintscited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 8; 2023: 5; 2024: 5; 2025: 3.

22 papers.

Sort:

  1. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 125
  2. 2022A Survey on Over-the-Air Computationcited by 19
  3. 2022Semi-Decentralized Federated Learning with Collaborative Relayingcited by 16
  4. 2024Trustworthy Federated Learning: Privacy, Security, and Beyondcited by 11
  5. 2023Over-the-Air Federated Learning and Optimizationcited by 10
  6. 2022Over-the-Air Ensemble Inference with Model Privacycited by 9
  7. 2022Robust Federated Learning with Connectivity Failures: A Semi-Decentralized Framework with Collaborative Relayingcited by 5
  8. 2022Differentially Private Federated Learning via Reconfigurable Intelligent Surfacecited by 5
  9. 2022Social-Aware Clustered Federated Learning with Customized Privacy Preservationcited by 5
  10. 2023Communication and Energy Efficient Wireless Federated Learning with Intrinsic Privacycited by 5
  11. 2023Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channelscited by 5
  12. 2024Private Collaborative Edge Inference via Over-the-Air Computationcited by 4
10 more
  1. 2022Privacy Amplification via Random Participation in Federated Learningcited by 2
  2. 2022On Differential Privacy for Federated Learning in Wireless Systems with Multiple Base Stationscited by 2
  3. 2023Binary Federated Learning with Client-Level Differential Privacycited by 2
  4. 2024Privacy Preserving Semi-Decentralized Mean Estimation over Intermittently-Connected Networkscited by 2
  5. 2023Differentially Private Wireless Federated Learning Using Orthogonal Sequencescited by 1
  6. 2024Collaborative Inference over Wireless Channels with Feature Differential Privacycited by 1
  7. 2024Providing Differential Privacy for Federated Learning Over Wireless: A Cross-layer Frameworkcited by 0
  8. 2025Privacy-Preserving Quantized Federated Learning with Diverse Precisioncited by 0
  9. 2025Communication-Learning Co-Design for Differentially Private Over-the-Air Federated Distillationcited by 0
  10. 2025Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participationcited by 0