mlsanityData to 7 Oct 2026

Communication Efficient Private Federated Learning Using Dithering

arXiv 2309.07809 ↗First posted 14 Sep 2023cs.LG cs.CRcited by 8

Not on the map. Why?

Abstract (arXiv)

The task of preserving privacy while ensuring efficient communication is a fundamental challenge in federated learning. In this work, we tackle this challenge in the trusted aggregator model, and propose a solution that achieves both objectives simultaneously. We show that employing a quantization scheme based on subtractive dithering at the clients can effectively replicate the normal noise addition process at the aggregator. This implies that we can guarantee the same level of differential privacy against other clients while substantially reducing the amount of communication required, as opposed to transmitting full precision gradients and using central noise addition. We also experimentally demonstrate that the accuracy of our proposed approach matches that of the full precision gradient method.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 20 of its 27 references that are in the map. First posted on arXiv 14 Sep 2023.

Builds on

20 of 27 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  5. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  6. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 375
  7. 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 237
  8. 2018Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoisingcited by 216
  9. 2019R'enyi Differential Privacy of the Sampled Gaussian Mechanismcited by 199
  10. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 188
  11. 2016Distributed Mean Estimation with Limited Communicationcited by 134
  12. 2022Reconstructing Training Data from Trained Neural Networkscited by 129
8 more
  1. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  2. 2019Natural Compression for Distributed Deep Learningcited by 88
  3. 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 34
  4. 2021Optimal Compression of Locally Differentially Private Mechanismscited by 22
  5. 2022Privacy-Aware Compression for Federated Data Analysiscited by 17
  6. 2023Fast Optimal Locally Private Mean Estimation via Random Projectionscited by 14
  7. 2021DP-REC: Private & Communication-Efficient Federated Learningcited by 10
  8. 2023Exact Optimality of Communication-Privacy-Utility Tradeoffs in Distributed Mean Estimationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 2; 2026: 3.

8 papers.

  1. 2023Compression with Exact Error Distribution for Federated Learningcited by 9
  2. 2024Universal Exact Compression of Differentially Private Mechanismscited by 8
  3. 2024The Rate-Distortion-Perception Trade-off: The Role of Private Randomnesscited by 6
  4. 2025Communication-Efficient and Privacy-Adaptable Mechanism for Federated Learningcited by 2
  5. 2026Communication-Efficient and Privacy-Adaptable Mechanism -- a Federated Learning Scheme with Convergence Analysiscited by 1
  6. 2025Federated learning over physical channels: adaptive algorithms with near-optimal guaranteescited by 0
  7. 2026Scalable Discrete-to-Continuous Channel Simulation for Compression and Privacycited by 0
  8. 2026Privacy-Aligned Personalized Federated Learning with Compact Adaptation and Variable-Length Gaussian Communicationcited by 0