mlsanityData to 7 Oct 2026

Privacy-Aware Compression for Federated Data Analysis

arXiv 2203.08134 ↗First posted 15 Mar 2022cs.LG cs.CRcited by 17

Not on the map. Why?

Abstract (arXiv)

Federated data analytics is a framework for distributed data analysis where a server compiles noisy responses from a group of distributed low-bandwidth user devices to estimate aggregate statistics. Two major challenges in this framework are privacy, since user data is often sensitive, and compression, since the user devices have low network bandwidth. Prior work has addressed these challenges separately by combining standard compression algorithms with known privacy mechanisms. In this work, we take a holistic look at the problem and design a family of privacy-aware compression mechanisms that work for any given communication budget. We first propose a mechanism for transmitting a single real number that has optimal variance under certain conditions. We then show how to extend it to metric differential privacy for location privacy use-cases, as well as vectors, for application to federated learning. Our experiments illustrate that our mechanism can lead to better utility vs. compression trade-offs for the same privacy loss in a number of settings.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 25 of its 43 references that are in the map. First posted on arXiv 15 Mar 2022.

Builds on

25 of 43 references.

References · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Deep Learning with Differential Privacycited by 2,682
  3. 2018Group Normalizationcited by 1,514
  4. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  5. 2017Renyi Differential Privacycited by 643
  6. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 262
  7. 2020Differentially Private Learning Needs Better Features (or Much More Data)cited by 233
  8. 2018Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoisingcited by 216
  9. 2020Federated Learning with Compression: Unified Analysis and Sharp Guaranteescited by 159
  10. 2020The Discrete Gaussian for Differential Privacycited by 134
  11. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
  12. 2020Tempered Sigmoid Activations for Deep Learning with Differential Privacycited by 121
13 more
  1. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 103
  2. 2021MARINA: Faster Non-Convex Distributed Learning with Compressioncited by 77
  3. 2019The Privacy Blanket of the Shuffle Modelcited by 73
  4. 2020Breaking the Communication-Privacy-Accuracy Trilemmacited by 68
  5. 2021The Skellam Mechanism for Differentially Private Federated Learningcited by 66
  6. 2019Stochastic Distributed Learning with Gradient Quantization and Variance Reductioncited by 64
  7. 2016Discrete Distribution Estimation under Local Privacycited by 58
  8. 2014Deep Roto-Translation Scattering for Object Classificationcited by 49
  9. 2020Faster Non-Convex Federated Learning via Global and Local Momentumcited by 48
  10. 2020Stochastic-Sign SGD for Federated Learning with Theoretical Guaranteescited by 34
  11. 2018Hadamard Response: Estimating Distributions Privately, Efficiently, and with Little Communicationcited by 26
  12. 2020Shuffled Model of Federated Learning: Privacy, Communication and Accuracy Trade-offscited by 15
  13. 2021Bit-efficient Numerical Aggregation and Stronger Privacy for Trust in Federated Analyticscited by 4

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 6; 2024: 6; 2025: 1.

17 papers.

Sort:

By area:

  1. 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 34
  2. 2023Randomized Quantization is All You Need for Differential Privacy in Federated Learningcited by 16
  3. 2023Fast Optimal Locally Private Mean Estimation via Random Projectionscited by 14
  4. 2023Compression with Exact Error Distribution for Federated Learningcited by 9
  5. 2023Communication Efficient Private Federated Learning Using Ditheringcited by 8
  6. 2024Universal Exact Compression of Differentially Private Mechanismscited by 8
  7. 2022Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Designcited by 6
  8. 2022Reconciling Security and Communication Efficiency in Federated Learningcited by 4
  9. 2024A survey on secure decentralized optimization and learningcited by 4
  10. 2023Breaking the Communication-Privacy-Accuracy Tradeoff with f-Differential Privacycited by 3
  11. 2024Enhancing Privacy in Federated Learning through Local Trainingcited by 3
  12. 2025Membership Inference Risks in Quantized Models: A Theoretical and Empirical Studycited by 3
5 more
  1. 2023Multi-Message Shuffled Privacy in Federated Learningcited by 2
  2. 2024TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Datacited by 2
  3. 2024Privacy-Aware Randomized Quantization via Linear Programmingcited by 1
  4. 2024On Using Secure Aggregation in Differentially Private Federated Learning with Multiple Local Stepscited by 1
  5. 2022On the Interaction Between Differential Privacy and Gradient Compression in Deep Learningcited by 0