Over-the-Air Federated Learning with Joint Adaptive Computation and Power Control
Not on the map. Why?
Abstract (arXiv)
This paper considers over-the-air federated learning (OTA-FL). OTA-FL exploits the superposition property of the wireless medium, and performs model aggregation over the air for free. Thus, it can greatly reduce the communication cost incurred in communicating model updates from the edge devices. In order to fully utilize this advantage while providing comparable learning performance to conventional federated learning that presumes model aggregation via noiseless channels, we consider the joint design of transmission scaling and the number of local iterations at each round, given the power constraint at each edge device. We first characterize the training error due to such channel noise in OTA-FL by establishing a fundamental lower bound for general functions with Lipschitz-continuous gradients. Then, by introducing an adaptive transceiver power scaling scheme, we propose an over-the-air federated learning algorithm with joint adaptive computation and power control (ACPC-OTA-FL). We provide the convergence analysis for ACPC-OTA-FL in training with non-convex objective functions and heterogeneous data. We show that the convergence rate of ACPC-OTA-FL matches that of FL with noise-free communications.
Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 16 of its 23 references that are in the map. First posted on arXiv 12 May 2022.
Builds on
16 of 23 references.
References · 16
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
- 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
- 2019Federated Machine Learning: Concept and Applicationscited by 412
- 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 278
- 2018Federated Learning via Over-the-Air Computationcited by 219
- 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 193
- 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 191
- 2019Federated Learning over Wireless Fading Channelscited by 183
- 2019Federated Learning for Wireless Communications: Motivation, Opportunities and Challengescited by 129
- 2020One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysiscited by 112
4 more
- 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 73
- 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 62
- 2016Over-the-air Function Computation in Sensor Networkscited by 11
- 2020Gradient Statistics Aware Power Control for Over-the-Air Federated Learningcited by 6
Built on by
Citing papers per year: 2023: 2; 2024: 4; 2025: 1; 2026: 2.
9 papers.
- 2023Over-the-Air Federated Learning and Optimizationcited by 10
- 2024Adaptive Federated Learning Over the Aircited by 4
- 2023Over-the-Air Federated Edge Learning with Error-Feedback One-Bit Quantization and Power Controlcited by 1
- 2024Scalable and Reliable Over-the-Air Federated Edge Learningcited by 1
- 2024Personalized Over-the-Air Federated Learning with Personalized Reconfigurable Intelligent Surfacescited by 0
- 2024Providing Differential Privacy for Federated Learning Over Wireless: A Cross-layer Frameworkcited by 0
- 2025Federated learning over physical channels: adaptive algorithms with near-optimal guaranteescited by 0
- 2026A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributionscited by 0
- 2026Channel-Adaptive Robust Aggregation for Over-the-Air Federated Learning in Heterogeneous Networkscited by 0
- 2026Channel-Adaptive Robust Aggregation for Over-the-Air Federated Learning in Heterogeneous Networks5 Jul 2026
- 2026A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions10 May 2026
- 2025Federated learning over physical channels: adaptive algorithms with near-optimal guarantees2 Sep 2025
- 2024Providing Differential Privacy for Federated Learning Over Wireless: A Cross-layer Framework5 Dec 2024
- 2024Scalable and Reliable Over-the-Air Federated Edge Learning16 Jul 2024
- 2024Adaptive Federated Learning Over the Air11 Mar 2024
- 2024Personalized Over-the-Air Federated Learning with Personalized Reconfigurable Intelligent Surfaces22 Jan 2024
- 2023Over-the-Air Federated Learning and Optimization16 Oct 2023
- 2023Over-the-Air Federated Edge Learning with Error-Feedback One-Bit Quantization and Power Control20 Mar 2023
Similar, not cited
Close in wording, no citation either way
- 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directions
- 2025Non-Convex Over-the-Air Heterogeneous Federated Learning: A Bias-Variance Trade-off
- 2025Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing
- 2025Noise Resilient Over-The-Air Federated Learning In Heterogeneous Wireless Networks
- 2025Learned Digital Codes for Over-the-Air Computation in Federated Edge Learning
- 2024Biased Over-the-Air Federated Learning under Wireless Heterogeneity
- 2022Over-the-Air Federated Learning via Second-Order Optimization
- 2025Learned Digital Over-the-Air Computing for Federated Edge Learning