mlsanityData to 7 Oct 2026

Adaptive Quantization of Model Updates for Communication-Efficient Federated Learning

arXiv 2102.04487 ↗First posted 8 Feb 2021cs.LG cs.DC stat.MLcited by 60

Not on the map. Why?

Abstract (arXiv)

Communication of model updates between client nodes and the central aggregating server is a major bottleneck in federated learning, especially in bandwidth-limited settings and high-dimensional models. Gradient quantization is an effective way of reducing the number of bits required to communicate each model update, albeit at the cost of having a higher error floor due to the higher variance of the stochastic gradients. In this work, we propose an adaptive quantization strategy called AdaQuantFL that aims to achieve communication efficiency as well as a low error floor by changing the number of quantization levels during the course of training. Experiments on training deep neural networks show that our method can converge in much fewer communicated bits as compared to fixed quantization level setups, with little or no impact on training and test accuracy.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). Builds on 19 of its 24 references that are in the map. First posted on arXiv 8 Feb 2021.

Builds on

19 of 24 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2019Advances and Open Problems in Federated Learningcited by 3,021
  6. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,140
  7. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  8. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  9. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
  10. 2017TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learningcited by 253
  11. 2019PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimizationcited by 234
  12. 2016QSGD: Communication-Efficient SGD via Gradient Quantization and Encodingcited by 147
7 more
  1. 2018ATOMO: Communication-efficient Learning via Atomic Sparsificationcited by 135
  2. 2016Distributed Mean Estimation with Limited Communicationcited by 134
  3. 2019Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronizationcited by 106
  4. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 103
  5. 2020Adaptive Gradient Quantization for Data-Parallel SGDcited by 43
  6. 2019Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradientscited by 32
  7. 2020Overlap Local-SGD: An Algorithmic Approach to Hide Communication Delays in Distributed SGDcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 12; 2023: 14; 2024: 17; 2025: 7; 2026: 5.

60 papers.

Sort:

By area:

  1. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 104
  2. 2023Towards Accurate Post-Training Quantization for Vision Transformercited by 70
  3. 2022Communication-Efficient Adaptive Federated Learningcited by 55
  4. 2021DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learningcited by 40
  5. 2022FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning Simulationscited by 27
  6. 2023Green Edge AI: A Contemporary Surveycited by 24
  7. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  8. 2021FedDQ: Communication-Efficient Federated Learning with Descending Quantizationcited by 18
  9. 2023Accelerating Hybrid Federated Learning Convergence under Partial Participationcited by 15
  10. 2024Distributed Deep Reinforcement Learning Based Gradient Quantization for Federated Learning Enabled Vehicle Edge Computingcited by 15
  11. 2022Adaptive Compression for Communication-Efficient Distributed Trainingcited by 14
  12. 2024Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimizationcited by 12
38 more
  1. 2024Green Federated Learning: A new era of Green Aware AIcited by 12
  2. 2022SAFARI: Sparsity enabled Federated Learning with Limited and Unreliable Communicationscited by 11
  3. 2023Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devicescited by 11
  4. 2024FADAS: Towards Federated Adaptive Asynchronous Optimizationcited by 10
  5. 2022Communication-Efficient Federated Learning With Data and Client Heterogeneitycited by 9
  6. 2024FedBAT: Communication-Efficient Federated Learning via Learnable Binarizationcited by 9
  7. 2022Distributed Linear Bandits under Communication Constraintscited by 8
  8. 2021Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimationcited by 7
  9. 2023A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regretcited by 7
  10. 2023AQUILA: Communication Efficient Federated Learning with Adaptive Quantization in Device Selection Strategycited by 7
  11. 2024Communication-Efficient Federated Low-Rank Update Algorithm and its Connection to Implicit Regularizationcited by 6
  12. 2022Over-the-Air Design of GAN Training for mmWave MIMO Channel Estimationcited by 5
  13. 2023Private Federated Learning with Autotuned Compressioncited by 5
  14. 2024FedAQ: Communication-Efficient Federated Edge Learning via Joint Uplink and Downlink Adaptive Quantizationcited by 5
  15. 2024FedDM: Enhancing Communication Efficiency and Handling Data Heterogeneity in Federated Diffusion Modelscited by 5
  16. 2024Exploring the Practicality of Federated Learning: A Survey Towards the Communication Perspectivecited by 4
  17. 2025FedRTS: Federated Robust Pruning via Combinatorial Thompson Samplingcited by 4
  18. 2022A-LAQ: Adaptive Lazily Aggregated Quantized Gradientcited by 3
  19. 2023Network Adaptive Federated Learning: Congestion and Lossy Compressioncited by 3
  20. 2023Sparse-SignSGD with Majority Vote for Communication-Efficient Distributed Learningcited by 3
  21. 2023FedDBL: Communication and Data Efficient Federated Deep-Broad Learning for Histopathological Tissue Classificationcited by 3
  22. 2024Energy-Efficient Channel Decoding for Wireless Federated Learning: Convergence Analysis and Adaptive Designcited by 3
  23. 2021Fundamental limits of over-the-air optimization: Are analog schemes optimal?cited by 2
  24. 2024SignSGD with Federated Votingcited by 2
  25. 2024Communication-Efficient Federated Learning with Adaptive Compression under Dynamic Bandwidthcited by 2
  26. 2022Communication-Efficient {Federated} Learning Using Censored Heavy Ball Descentcited by 1
  27. 2022Prototype-Based Layered Federated Cross-Modal Hashingcited by 1
  28. 2022Optimal Privacy Preserving for Federated Learning in Mobile Edge Computingcited by 1
  29. 2024Towards Communication-efficient Federated Learning via Sparse and Aligned Adaptive Optimizationcited by 1
  30. 2024Adaptive Quantization Resolution and Power Control for Federated Learning over Cell-free Networkscited by 1
  31. 2024Accelerating Energy-Efficient Federated Learning in Cell-Free Networks with Adaptive Quantizationcited by 1
  32. 2025Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimizationcited by 1
  33. 2025FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initializationcited by 1
  34. 2025Pareto Actor-Critic for Communication and Computation Co-Optimization in Non-Cooperative Federated Learning Servicescited by 1
  35. 2025FedBiF: Communication-Efficient Federated Learning via Bits Freezingcited by 1
  36. 2026Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacycited by 1
  37. 2021Federated Learning with Superquantile Aggregation for Heterogeneous Datacited by 0
  38. 2023Federated Learning for Energy Constrained IoT devices: A systematic mapping studycited by 0

50 most cited of 60 All 60 (JSON)