mlsanityData to 14 Oct 2026

Communication-Efficient and Privacy-Adaptable Mechanism for Federated Learning

arXiv 2501.12046 ↗First posted 21 Jan 2025cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Training machine learning models on decentralized private data via federated learning (FL) poses two key challenges: communication efficiency and privacy protection. In this work, we address these challenges within the trusted aggregator model by introducing a novel approach called the Communication-Efficient and Privacy-Adaptable Mechanism (CEPAM), achieving both objectives simultaneously. In particular, CEPAM leverages the rejection-sampled universal quantizer (RSUQ), a construction of randomized vector quantizer whose resulting distortion is equivalent to a prescribed noise, such as Gaussian or Laplace noise, enabling joint differential privacy and compression. Our CEPAM provides the additional benefit of privacy adaptability, allowing clients and the server to customize privacy protection based on required accuracy and protection. We theoretically analyze the privacy guarantee of CEPAM and investigate the trade-offs among user privacy and accuracy of CEPAM through experimental evaluations. Moreover, we assess CEPAM's utility performance using MNIST dataset, demonstrating that CEPAM surpasses baseline models in terms of learning accuracy.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 33 of its 72 references that are in the map. First posted on arXiv 21 Jan 2025.

Builds on

33 of 72 references.

References · 33

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2016Deep Learning with Differential Privacycited by 2,728
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  5. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  6. 2019Deep Leakage from Gradientscited by 1,021
  7. 2017Renyi Differential Privacycited by 650
  8. 2018Local SGD Converges Fast and Communicates Littlecited by 605
  9. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 478
  10. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  11. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  12. 2018Sparsified SGD with Memorycited by 376
21 more
  1. 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 242
  2. 2018Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoisingcited by 218
  3. 2017Gradient Sparsification for Communication-Efficient Distributed Optimizationcited by 201
  4. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  5. 2016Practical Secure Aggregation for Federated Learning on User-Held Datacited by 178
  6. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 107
  7. 2018Privacy Amplification by Iterationcited by 100
  8. 2021The Skellam Mechanism for Differentially Private Federated Learningcited by 68
  9. 2020Universally Quantized Neural Compressioncited by 64
  10. 2018Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameterscited by 58
  11. 2021Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communicationcited by 39
  12. 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 35
  13. 2021Optimal Compression of Locally Differentially Private Mechanismscited by 22
  14. 2023Compression with Exact Error Distribution for Federated Learningcited by 11
  15. 2023Communication-Efficient Laplace Mechanism for Differential Privacy via Random Quantizationcited by 9
  16. 2023Communication Efficient Private Federated Learning Using Ditheringcited by 9
  17. 2024Universal Exact Compression of Differentially Private Mechanismscited by 8
  18. 2023Layered Randomized Quantization for Communication-Efficient and Privacy-Preserving Distributed Learningcited by 6
  19. 2017Distributed deep learning on edge-devices: feasibility via adaptive compressioncited by 5
  20. 2024Rejection-Sampled Universal Quantization for Smaller Quantization Errorscited by 4
  21. 2019Elliptical Perturbations for Differential Privacycited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Communication-Efficient and Privacy-Adaptable Mechanism -- a Federated Learning Scheme with Convergence Analysiscited by 1
  2. 2026Scalable Discrete-to-Continuous Channel Simulation for Compression and Privacycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy
  2. 2024CorBin-FL: A Differentially Private Federated Learning Mechanism using Common Randomness
  3. 2025Privacy-Preserving Decentralized Federated Learning via Explainable Adaptive Differential Privacy
  4. 2025Privacy-Preserving Quantized Federated Learning with Diverse Precision
  5. 2024The Effect of Quantization in Federated Learning: A R'enyi Differential Privacy Perspective
  6. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation
  7. 2023Randomized Quantization is All You Need for Differential Privacy in Federated Learning
  8. 2023QMGeo: Differentially Private Federated Learning via Stochastic Quantization with Mixed Truncated Geometric Distribution