mlsanityData to 7 Oct 2026

Federated Learning over Noisy Channels: Convergence Analysis and Design Examples

arXiv 2101.02198 ↗First posted 6 Jan 2021cs.IT cs.LG cs.NIcited by 8

Not on the map. Why?

Abstract (arXiv)

Does Federated Learning (FL) work when both uplink and downlink communications have errors? How much communication noise can FL handle and what is its impact to the learning performance? This work is devoted to answering these practically important questions by explicitly incorporating both uplink and downlink noisy channels in the FL pipeline. We present several novel convergence analyses of FL over simultaneous uplink and downlink noisy communication channels, which encompass full and partial clients participation, direct model and model differential transmissions, and non-independent and identically distributed (IID) local datasets. These analyses characterize the sufficient conditions for FL over noisy channels to have the same convergence behavior as the ideal case of no communication error. More specifically, in order to maintain the O(1/T) convergence rate of FedAvg with perfect communications, the uplink and downlink signal-to-noise ratio (SNR) for direct model transmissions should be controlled such that they scale as O(t^2) where t is the index of communication rounds, but can stay constant for model differential transmissions. The key insight of these theoretical results is a "flying under the radar" principle - stochastic gradient descent (SGD) is an inherent noisy process and uplink/downlink communication noises can be tolerated as long as they do not dominate the time-varying SGD noise. We exemplify these theoretical findings with two widely adopted communication techniques - transmit power control and diversity combining - and further validating their performance advantages over the standard methods via extensive numerical experiments using several real-world FL tasks.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 52 of its 65 references that are in the map. First posted on arXiv 6 Jan 2021.

Builds on

52 of 65 references.

References · 52

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  5. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  6. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  7. 2019Towards Federated Learning at Scale: System Designcited by 826
  8. 2018LEAF: A Benchmark for Federated Settingscited by 780
  9. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  10. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 541
  11. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  12. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 407
38 more
  1. 2019Fair Resource Allocation in Federated Learningcited by 389
  2. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
  3. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 347
  4. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 262
  5. 2018Federated Learning via Over-the-Air Computationcited by 215
  6. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
  7. 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
  8. 2019On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimizationcited by 178
  9. 2019Federated Learning over Wireless Fading Channelscited by 178
  10. 2018Expanding the Reach of Federated Learning by Reducing Client Resource Requirementscited by 162
  11. 2016QSGD: Communication-Efficient SGD via Gradient Quantization and Encodingcited by 147
  12. 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
  13. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 127
  14. 2020One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysiscited by 108
  15. 2018Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithmscited by 106
  16. 2019Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronizationcited by 106
  17. 2020Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspectivecited by 102
  18. 2019DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compressioncited by 98
  19. 2018Towards an Intelligent Edge: Wireless Communication Meets Machine Learningcited by 94
  20. 2017On the convergence properties of a K-step averaging stochastic gradient descent algorithm for nonconvex optimizationcited by 91
  21. 2020Convergence Time Optimization for Federated Learning over Wireless Networkscited by 81
  22. 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 72
  23. 2015Perturbed Iterate Analysis for Asynchronous Stochastic Optimizationcited by 67
  24. 2020Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneitycited by 56
  25. 2020Federated Learning With Quantized Global Model Updatescited by 54
  26. 2020Design and Analysis of Uplink and Downlink Communications for Federated Learningcited by 48
  27. 2019Device Scheduling with Fast Convergence for Wireless Federated Learningcited by 46
  28. 2019Energy-Efficient Radio Resource Allocation for Federated Edge Learningcited by 39
  29. 2019Robust Federated Learning with Noisy Communicationcited by 33
  30. 2019High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learningcited by 32
  31. 2020Energy-Efficient Federated Edge Learning with Joint Communication and Computation Designcited by 30
  32. 2020Convergence of Federated Learning over a Noisy Downlinkcited by 29
  33. 2019Energy-Aware Analog Aggregation for Federated Learning with Redundant Datacited by 23
  34. 2018Double Quantization for Communication-Efficient Distributed Optimizationcited by 18
  35. 2020Fast Convergence Algorithm for Analog Federated Learningcited by 16
  36. 2019Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Aircited by 10
  37. 2020Cluster-Based Cooperative Digital Over-the-Air Aggregation for Wireless Federated Edge Learningcited by 6
  38. 2020Optimized Power Control for Over-the-Air Federated Edge Learningcited by 3

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 1; 2023: 2; 2024: 2.

8 papers.

  1. 2021Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysiscited by 51
  2. 2023On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharingcited by 16
  3. 2021A Hybrid Architecture for Federated and Centralized Learningcited by 8
  4. 2022Federated Multi-Armed Bandits Under Byzantine Attackscited by 6
  5. 2021Resource Rationing for Wireless Federated Learning: Concept, Benefits, and Challengescited by 4
  6. 2023Improved Convergence Analysis and SNR Control Strategies for Federated Learning in the Presence of Noisecited by 4
  7. 2024Energy-Efficient Channel Decoding for Wireless Federated Learning: Convergence Analysis and Adaptive Designcited by 3
  8. 2024Noise-Robust and Resource-Efficient ADMM-based Federated Learningcited by 1