mlsanityData to 7 Oct 2026

Joint Optimization of Communications and Federated Learning Over the Air

arXiv 2104.03490 ↗First posted 8 Apr 2021cs.LG cs.DCcited by 13

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is an attractive paradigm for making use of rich distributed data while protecting data privacy. Nonetheless, nonideal communication links and limited transmission resources may hinder the implementation of fast and accurate FL. In this paper, we study joint optimization of communications and FL based on analog aggregation transmission in realistic wireless networks. We first derive closed-form expressions for the expected convergence rate of FL over the air, which theoretically quantify the impact of analog aggregation on FL. Based on the analytical results, we develop a joint optimization model for accurate FL implementation, which allows a parameter server to select a subset of workers and determine an appropriate power scaling factor. Since the practical setting of FL over the air encounters unobservable parameters, we reformulate the joint optimization of worker selection and power allocation using controlled approximation. Finally, we efficiently solve the resulting mixed-integer programming problem via a simple yet optimal finite-set search method by reducing the search space. Simulation results show that the proposed solutions developed for realistic wireless analog channels outperform a benchmark method, and achieve comparable performance of the ideal case where FL is implemented over noise-free wireless channels.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 26 of its 41 references that are in the map. First posted on arXiv 8 Apr 2021.

Builds on

26 of 41 references.

References · 26

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  3. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,140
  4. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  5. 2018Sparsified SGD with Memorycited by 373
  6. 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 262
  7. 2017Sparse Communication for Distributed Gradient Descentcited by 243
  8. 2018The Convergence of Sparsified Gradient Methodscited by 228
  9. 2018Federated Learning via Over-the-Air Computationcited by 215
  10. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
  11. 2019Federated Learning over Wireless Fading Channelscited by 178
  12. 2013On the Convergence of Decentralized Gradient Descentcited by 158
14 more
  1. 2016QSGD: Communication-Efficient SGD via Gradient Quantization and Encodingcited by 147
  2. 2013Communication Efficient Distributed Optimization using an Approximate Newton-type Methodcited by 131
  3. 2018Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithmscited by 106
  4. 2019DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compressioncited by 98
  5. 2018LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learningcited by 95
  6. 2018Towards an Intelligent Edge: Wireless Communication Meets Machine Learningcited by 94
  7. 2018Wireless Network Intelligence at the Edgecited by 90
  8. 2019Energy-Efficient Radio Resource Allocation for Federated Edge Learningcited by 39
  9. 2018Communication-Computation Efficient Gradient Codingcited by 26
  10. 2019Cell-Free Massive MIMO for Wireless Federated Learningcited by 25
  11. 2019Energy-Aware Analog Aggregation for Federated Learning with Redundant Datacited by 23
  12. 2014Asynchronous Stochastic Coordinate Descent: Parallelism and Convergence Propertiescited by 21
  13. 2019On Maintaining Linear Convergence of Distributed Learning and Optimization under Limited Communicationcited by 15
  14. 2019Collaborative Machine Learning at the Wireless Edge with Blind Transmitterscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 4; 2024: 3; 2025: 1; 2026: 1.

13 papers.

Sort:

  1. 2021Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applicationscited by 96
  2. 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directionscited by 21
  3. 2022Over-the-Air Federated Learning via Second-Order Optimizationcited by 11
  4. 2023Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learningcited by 9
  5. 2021BEV-SGD: Best Effort Voting SGD for Analog Aggregation Based Federated Learning against Byzantine Attackerscited by 6
  6. 2022Energy and Spectrum Efficient Federated Learning via High-Precision Over-the-Air Computationcited by 6
  7. 2024Multiple Access in the Era of Distributed Computing and Edge Intelligencecited by 4
  8. 2024Distributed Swarm Learning for Edge Internet of Thingscited by 4
  9. 2023Over-the-Air Federated Averaging with Limited Power and Privacy Budgetscited by 1
  10. 2023Semi-Federated Learning: Convergence Analysis and Optimization of A Hybrid Learning Frameworkcited by 0
  11. 2024Waveform Design for Over-the-Air Computingcited by 0
  12. 2025Multi-Worker Selection based Distributed Swarm Learning for Edge IoT with Non-i.i.d. Datacited by 0
1 more
  1. 2026Hidden in Rounds: Predicting the Time Cost of 802.11 Contention in Federated Learningcited by 0