mlsanityData to 14 Oct 2026

Quantization in Federated Learning: Methods, Challenges and Future Directions

arXiv 2606.26822 ↗First posted 25 Jun 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) has become a foundational paradigm for privacy-preserving distributed intelligence, yet its scalability remains fundamentally constrained by communication bottlenecks, device heterogeneity, and the challenges of training under statistically non-IID data. Quantization is one of the most effective mechanisms for mitigating these limitations, reducing both uplink/downlink payloads and on-device computation. This paper provides the first FL-centric systematic review of quantization, introducing a novel taxonomy organized around FL-specific dimensions, including client heterogeneity, aggregation consistency, communication-scheduling adaptation, non-IID robustness, privacy/security integration, and hardware/energy co-optimization. Beyond cataloging existing methods, we analyze how quantization interacts with core FL behaviors such as client drift, partial participation, convergence stability, secure aggregation, and differential privacy. We further identify cross-method insights, open research gaps, and design guidelines for practitioners deploying quantized FL on mobile, IoT, and edge platforms. This survey thus establishes quantization not merely as a compression technique, but as a fundamental systems component shaping the performance, robustness, and practicality of modern FL.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 65 of its 123 references that are in the map. First posted on arXiv 25 Jun 2026.

Builds on

65 of 123 references.

References · 65

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  5. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  6. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  7. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  8. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  9. 2018Federated Learning with Non-IID Datacited by 1,108
  10. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  11. 2018LEAF: A Benchmark for Federated Settingscited by 792
  12. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
38 more
  1. 2019Learned Step Size Quantizationcited by 628
  2. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 621
  3. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
  4. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 478
  5. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
  6. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
  7. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 402
  8. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
  9. 2020SplitFed: When Federated Learning Meets Split Learningcited by 310
  10. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 252
  11. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 180
  12. 2019Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networkscited by 148
  13. 2020Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challengescited by 139
  14. 2019Federated Learning for Wireless Communications: Motivation, Opportunities and Challengescited by 129
  15. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 107
  16. 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 66
  17. 2021Adaptive Quantization of Model Updates for Communication-Efficient Federated Learningcited by 63
  18. 2020Ternary Compression for Communication-Efficient Federated Learningcited by 57
  19. 2020Federated Learning With Quantized Global Model Updatescited by 55
  20. 2018Value-aware Quantization for Training and Inference of Neural Networkscited by 52
  21. 2021Communication Efficiency in Federated Learning: Achievements and Challengescited by 40
  22. 2023Federated Learning for Computationally-Constrained Heterogeneous Devices: A Surveycited by 40
  23. 2024Advances and Open Challenges in Federated Foundation Modelscited by 36
  24. 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 35
  25. 2020Federated Learning for 6G Communications: Challenges, Methods, and Future Directionscited by 33
  26. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  27. 2022Towards Efficient Communications in Federated Learning: A Contemporary Surveycited by 24
  28. 2023Topology-aware Federated Learning in Edge Computing: A Comprehensive Surveycited by 23
  29. 2020Secure Aggregation with Heterogeneous Quantization in Federated Learningcited by 21
  30. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  31. 2021FedDQ: Communication-Efficient Federated Learning with Descending Quantizationcited by 20
  32. 2019Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learningcited by 18
  33. 2021Communication-Efficient Federated Learning via Quantized Compressed Sensingcited by 18
  34. 2022Dynamic Split Computing for Efficient Deep Edge Intelligencecited by 18
  35. 2022Wireless Quantized Federated Learning: A Joint Computation and Communication Designcited by 15
  36. 2022Communication-Efficient Federated Learning for Heterogeneous Edge Devices Based on Adaptive Gradient Quantizationcited by 14
  37. 2022Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devicescited by 12
  38. 2022Federated Learning and Meta Learning: Approaches, Applications, and Directionscited by 12

50 most cited of 65 All 65 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Privacy-Preserving Quantized Federated Learning with Diverse Precision
  2. 2024FedFQ: Federated Learning with Fine-Grained Quantization
  3. 2023Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data Heterogeneity
  4. 2022Performance Optimization for Variable Bitwidth Federated Learning in Wireless Networks
  5. 2025Federated Learning: A Survey on Privacy-Preserving Collaborative Intelligence
  6. 2022Optimal Privacy Preserving for Federated Learning in Mobile Edge Computing
  7. 2024The Effect of Quantization in Federated Learning: A R'enyi Differential Privacy Perspective
  8. 2025FedHQ: Hybrid Runtime Quantization for Federated Learning