mlsanityData to 7 Oct 2026

FedDQ: Communication-Efficient Federated Learning with Descending Quantization

arXiv 2110.02291 ↗First posted 5 Oct 2021cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is an emerging learning paradigm without violating users' privacy. However, large model size and frequent model aggregation cause serious communication bottleneck for FL. To reduce the communication volume, techniques such as model compression and quantization have been proposed. Besides the fixed-bit quantization, existing adaptive quantization schemes use ascending-trend quantization, where the quantization level increases with the training stages. In this paper, we first investigate the impact of quantization on model convergence, and show that the optimal quantization level is directly related to the range of the model updates. Given the model is supposed to converge with the progress of the training, the range of the model updates will gradually shrink, indicating that the quantization level should decrease with the training stages. Based on the theoretical analysis, a descending quantization scheme named FedDQ is proposed. Experimental results show that the proposed descending quantization scheme can save up to 65.2% of the communicated bit volume and up to 68% of the communication rounds, when compared with existing schemes.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 13 of its 18 references that are in the map. First posted on arXiv 5 Oct 2021.

Builds on

13 of 18 references.

References · 13

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2019Advances and Open Problems in Federated Learningcited by 3,021
  5. 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 561
  6. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
  7. 2017Sparse Communication for Distributed Gradient Descentcited by 243
  8. 2020Federated Learning with Compression: Unified Analysis and Sharp Guaranteescited by 159
  9. 2016Distributed Mean Estimation with Limited Communicationcited by 134
  10. 2019One-Shot Federated Learningcited by 124
  11. 2021Adaptive Quantization of Model Updates for Communication-Efficient Federated Learningcited by 60
  12. 2020Ternary Compression for Communication-Efficient Federated Learningcited by 57
1 more
  1. 2018MQGrad: Reinforcement Learning of Gradient Quantization in Parameter Servercited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 7; 2025: 4; 2026: 3.

18 papers.

Sort:

  1. 2022Adaptive Compression for Communication-Efficient Distributed Trainingcited by 14
  2. 2024Green Federated Learning: A new era of Green Aware AIcited by 12
  3. 2022Service Delay Minimization for Federated Learning over Mobile Devicescited by 9
  4. 2024FedBAT: Communication-Efficient Federated Learning via Learnable Binarizationcited by 9
  5. 2023AQUILA: Communication Efficient Federated Learning with Adaptive Quantization in Device Selection Strategycited by 7
  6. 2024Queuing dynamics of asynchronous Federated Learningcited by 6
  7. 2024FedAQ: Communication-Efficient Federated Edge Learning via Joint Uplink and Downlink Adaptive Quantizationcited by 5
  8. 2024Energy-Efficient Channel Decoding for Wireless Federated Learning: Convergence Analysis and Adaptive Designcited by 3
  9. 2025Optimizing Asynchronous Federated Learning: A Delicate Trade-Off Between Model-Parameter Staleness and Update Frequencycited by 2
  10. 2023FAVANO: Federated AVeraging with Asynchronous NOdescited by 1
  11. 2024Adaptive Quantization Resolution and Power Control for Federated Learning over Cell-free Networkscited by 1
  12. 2024Accelerating Energy-Efficient Federated Learning in Cell-Free Networks with Adaptive Quantizationcited by 1
6 more
  1. 2025FedBiF: Communication-Efficient Federated Learning via Bits Freezingcited by 1
  2. 2026Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacycited by 1
  3. 2025Enhancing Communication Efficiency in FL with Adaptive Gradient Quantization and Communication Frequency Optimizationcited by 0
  4. 2025FedLAM: Low-latency Wireless Federated Learning via Layer-wise Adaptive Modulationcited by 0
  5. 2026Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networkscited by 0
  6. 2026Quantization in Federated Learning: Methods, Challenges and Future Directionscited by 0