mlsanityData to 14 Oct 2026

Design and Analysis of Uplink and Downlink Communications for Federated Learning

arXiv 2012.04057 ↗First posted 7 Dec 2020cs.IT cs.LG eess.SPcited by 48

Not on the map. Why?

Abstract (arXiv)

Communication has been known to be one of the primary bottlenecks of federated learning (FL), and yet existing studies have not addressed the efficient communication design, particularly in wireless FL where both uplink and downlink communications have to be considered. In this paper, we focus on the design and analysis of physical layer quantization and transmission methods for wireless FL. We answer the question of what and how to communicate between clients and the parameter server and evaluate the impact of the various quantization and transmission options of the updated model on the learning performance. We provide new convergence analysis of the well-known FedAvg under non-i.i.d. dataset distributions, partial clients participation, and finite-precision quantization in uplink and downlink communications. These analyses reveal that, in order to achieve an O(1/T) convergence rate with quantization, transmitting the weight requires increasing the quantization level at a logarithmic rate, while transmitting the weight differential can keep a constant quantization level. Comprehensive numerical evaluation on various real-world datasets reveals that the benefit of a FL-tailored uplink and downlink communication design is enormous - a carefully designed quantization and transmission achieves more than 98% of the floating-point baseline accuracy with fewer than 10% of the baseline bandwidth, for majority of the experiments on both i.i.d. and non-i.i.d. datasets. In particular, 1-bit quantization (3.1% of the floating-point baseline bandwidth) achieves 99.8% of the floating-point baseline accuracy at almost the same convergence rate on MNIST, representing the best known bandwidth-accuracy tradeoff to the best of the authors' knowledge.

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 6; 2023: 10; 2024: 9; 2025: 6; 2026: 6.

48 papers.

Sort:

  1. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 129
  2. 2021Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applicationscited by 97
  3. 2021Federated Learning: A Signal Processing Perspectivecited by 49
  4. 2021Communication Efficiency in Federated Learning: Achievements and Challengescited by 40
  5. 2021Quantized Federated Learning under Transmission Delay and Outage Constraintscited by 37
  6. 2022Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directionscited by 35
  7. 2023Why Batch Normalization Damage Federated Learning on Non-IID Data?cited by 29
  8. 2023Machine Learning for Large-Scale Optimization in 6G Wireless Networkscited by 18
  9. 2023On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharingcited by 16
  10. 2022Wireless Quantized Federated Learning: A Joint Computation and Communication Designcited by 15
  11. 2022Green, Quantized Federated Learning over Wireless Networks: An Energy-Efficient Designcited by 15
  12. 2021On the Tradeoff between Energy, Precision, and Accuracy in Federated Quantized Neural Networkscited by 10
36 more
  1. 2021Computational Intelligence and Deep Learning for Next-Generation Edge-Enabled Industrial IoTcited by 9
  2. 2021Federated Learning over Noisy Channels: Convergence Analysis and Design Examplescited by 8
  3. 2021Federated Gaussian Process: Convergence, Automatic Personalization and Multi-fidelity Modelingcited by 8
  4. 2023Making Batch Normalization Great in Federated Deep Learningcited by 8
  5. 2023A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regretcited by 7
  6. 2021FedFog: Network-Aware Optimization of Federated Learning over Wireless Fog-Cloud Systemscited by 6
  7. 2024Energy-Efficient Federated Edge Learning with Streaming Data: A Lyapunov Optimization Approachcited by 6
  8. 2024Communication-Efficient Federated Low-Rank Update Algorithm and its Connection to Implicit Regularizationcited by 6
  9. 2021Resource Rationing for Wireless Federated Learning: Concept, Benefits, and Challengescited by 4
  10. 2023Improved Convergence Analysis and SNR Control Strategies for Federated Learning in the Presence of Noisecited by 4
  11. 2022Towards cost-effective and resource-aware aggregation at Edge for Federated Learningcited by 3
  12. 2023Gradient Sparsification for Efficient Wireless Federated Learning with Differential Privacycited by 3
  13. 2024Energy-Efficient Channel Decoding for Wireless Federated Learning: Convergence Analysis and Adaptive Designcited by 3
  14. 2025Federated Split Learning with Improved Communication and Storage Efficiencycited by 3
  15. 2023Straggler-resilient Federated Learning: Tackling Computation Heterogeneity with Layer-wise Partial Model Training in Mobile Edge Networkcited by 2
  16. 2024FedNMUT -- Federated Noisy Model Update Tracking Convergence Analysiscited by 2
  17. 2025Communication-Efficient Federated Learning by Quantized Variance Reduction for Heterogeneous Wireless Edge Networkscited by 2
  18. 2025FedFetch: Faster Federated Learning with Adaptive Downstream Prefetchingcited by 2
  19. 2023Differentially Private Wireless Federated Learning Using Orthogonal Sequencescited by 1
  20. 2023Harnessing the Power of Federated Learning in Federated Contextual Banditscited by 1
  21. 2024Towards Federated Learning with On-device Training and Communication in 8-bit Floating Pointcited by 1
  22. 2024SCALE: Self-regulated Clustered federAted LEarning in a Homogeneous Environmentcited by 1
  23. 2024Noise-Robust and Resource-Efficient ADMM-based Federated Learningcited by 1
  24. 2022Efficient Adaptive Federated Optimization of Federated Learning for IoTcited by 0
  25. 2022Random Orthogonalization for Federated Learning in Massive MIMO Systemscited by 0
  26. 2024Digital versus Analog Transmissions for Federated Learning over Wireless Networkscited by 0
  27. 2024An Autoencoder-Based Constellation Design for AirComp in Wireless Federated Learningcited by 0
  28. 2025Lightweight Federated Learning over Wireless Edge Networkscited by 0
  29. 2025Energy-Efficient Federated Learning for Edge Real-Time Vision via Joint Data, Computation, and Communication Designcited by 0
  30. 2025Energy-Efficient Quantized Federated Learning for Resource-constrained IoT devicescited by 0
  31. 2026Distributed Perceptron under Bounded Staleness, Partial Participation, and Noisy Communicationcited by 0
  32. 2026Prioritizing Gradient Sign Over Modulus: An Importance-Aware Framework for Wireless Federated Learningcited by 0
  33. 2026Mixed-Timescale Differential Coding for Downlink Model Broadcast in Wireless Federated Learningcited by 0
  34. 2026GQ-FSL: Green Quantized Federated Split Learning Framework for Wireless Edge Networkscited by 0
  35. 2026Polar Code Based Federated Learning: Convergence Analysis and Resource Allocationcited by 0
  36. 2026Communication-Efficient Agnostic Federated Learning via Faster Convergence and Compressioncited by 0