mlsanityData to 14 Oct 2026

Privacy-Preserving Quantized Federated Learning with Diverse Precision

arXiv 2507.00920 ↗First posted 1 Jul 2025cs.LG eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) has emerged as a promising paradigm for distributed machine learning, enabling collaborative training of a global model across multiple local devices without requiring them to share raw data. Despite its advancements, FL is limited by factors such as: (i) privacy risks arising from the unprotected transmission of local model updates to the fusion center (FC) and (ii) decreased learning utility caused by heterogeneity in model quantization resolution across participating devices. Prior work typically addresses only one of these challenges because maintaining learning utility under both privacy risks and quantization heterogeneity is a non-trivial task. In this paper, our aim is therefore to improve the learning utility of a privacy-preserving FL that allows clusters of devices with different quantization resolutions to participate in each FL round. Specifically, we introduce a novel stochastic quantizer (SQ) that is designed to simultaneously achieve differential privacy (DP) and minimum quantization error. Notably, the proposed SQ guarantees bounded distortion, unlike other DP approaches. To address quantization heterogeneity, we introduce a cluster size optimization technique combined with a linear fusion approach to enhance model aggregation accuracy. Numerical simulations validate the benefits of our approach in terms of privacy protection and learning utility compared to the conventional LaplaceSQ-FL algorithm.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 50 references that are in the map. First posted on arXiv 1 Jul 2025.

Builds on

30 of 50 references.

References · 30

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  4. 2019Deep Leakage from Gradientscited by 1,021
  5. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  6. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  7. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
  8. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 252
  9. 2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
  10. 2020On Biased Compression for Distributed Learningcited by 140
  11. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 128
  12. 2024OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learningcited by 128
18 more
  1. 2021FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Taskscited by 85
  2. 2023Revisiting Gradient Clipping: Stochastic bias and tight convergence guaranteescited by 83
  3. 2020Breaking the Communication-Privacy-Accuracy Trilemmacited by 68
  4. 2020Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Controlcited by 63
  5. 2021Federated Learning: A Signal Processing Perspectivecited by 49
  6. 2023A Guide Through the Zoo of Biased SGDcited by 40
  7. 2023Federated Learning for Connected and Automated Vehicles: A Survey of Existing Approaches and Challengescited by 40
  8. 2021Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communicationcited by 39
  9. 2021Quantized Federated Learning under Transmission Delay and Outage Constraintscited by 37
  10. 2022Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directionscited by 35
  11. 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 35
  12. 2020Federated Learning and Wireless Communicationscited by 27
  13. 2020Pretraining Federated Text Models for Next Word Predictioncited by 22
  14. 2021Privacy Amplification for Federated Learning via User Sampling and Wireless Aggregationcited by 22
  15. 2023Randomized Quantization is All You Need for Differential Privacy in Federated Learningcited by 17
  16. 2020Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noisecited by 15
  17. 2023Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learningcited by 14
  18. 2023QMGeo: Differentially Private Federated Learning via Stochastic Quantization with Mixed Truncated Geometric Distributioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024The Effect of Quantization in Federated Learning: A R'enyi Differential Privacy Perspective
  2. 2024CorBin-FL: A Differentially Private Federated Learning Mechanism using Common Randomness
  3. 2026Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy
  4. 2026Quantization in Federated Learning: Methods, Challenges and Future Directions
  5. 2022sqSGD: Locally Private and Communication Efficient Federated Learning
  6. 2024Promoting Data and Model Privacy in Federated Learning through Quantized LoRA
  7. 2025Enhancing Model Privacy in Federated Learning with Random Masking and Quantization
  8. 2026Communication-Efficient and Privacy-Adaptable Mechanism -- a Federated Learning Scheme with Convergence Analysis