CFLIT: Coexisting Federated Learning and Information Transfer
- 4 April 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 22 (11) , 8436-8453
Abstract
Future wireless networks are expected to support diverse mobile services, including artificial intelligence (AI) services and ubiquitous data transmissions. Federated learning (FL), as a revolutionary learning approach, enables collaborative AI model training across distributed mobile edge devices. By exploiting the superposition property of multiple-access channels, over-the-air computation allows concurrent model uploading from massive devices over the same radio resources, and thus significantly reduces the communication cost of FL. In this paper, we study the coexistence of over-the-air FL and traditional information transfer (IT) in a mobile edge network, where an access point (AP) coordinates a set of devices for over-the-air FL and serves multiple devices for information transfer in the meantime. We propose a coexisting federated learning and information transfer (CFLIT) communication framework, where the FL and IT devices share the wireless spectrum in an orthogonal frequency division multiplexing (OFDM) system. Under this framework, we aim to maximize the IT data rate and guarantee a given FL convergence performance by optimizing the long-term radio resource allocation. A key challenge that limits the spectrum efficiency of the coexisting system lies in the large overhead incurred by frequent communication between the server and edge devices for FL model aggregation. To address the challenge, we rigorously analyze the impact of the computation-to-communication ratio on the convergence of over-the-air FL in wireless fading channels. The analysis reveals the existence of an optimal computation-to-communication ratio that minimizes the amount of radio resources needed for over-the-air FL to converge to a given error tolerance. Based on the analysis, we propose a low-complexity online algorithm to jointly optimize the radio resource allocation for both the FL devices and IT devices. We further derive an analytical expression of the achievable data rate of IT users. Extensive numerical simulations verify the superior performance of the proposed design for the coexistence of FL and IT devices in wireless cellular systems.Keywords
All Related Versions
Funding Information
- General Research Fund (14201920, 14202421, 14214122)
- Area of Excellence Scheme (AoE/E-601/22-R)
- Research Grants Council of Hong Kong
This publication has 27 references indexed in Scilit:
- Federated Learning Over Wireless Fading ChannelsIEEE Transactions on Wireless Communications, 2020
- Federated Learning via Over-the-Air ComputationIEEE Transactions on Wireless Communications, 2020
- Broadband Analog Aggregation for Low-Latency Federated Edge LearningIEEE Transactions on Wireless Communications, 2019
- A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research ProblemsIEEE Network, 2019
- Wireless Network Intelligence at the EdgeProceedings of the IEEE, 2019
- The Roadmap to 6G: AI Empowered Wireless NetworksIEEE Communications Magazine, 2019
- Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge ComputingProceedings of the IEEE, 2019
- Adaptive Federated Learning in Resource Constrained Edge Computing SystemsIEEE Journal on Selected Areas in Communications, 2019
- Memristor-Based Multilayer Neural Networks With Online Gradient Descent TrainingIEEE Transactions on Neural Networks and Learning Systems, 2015
- Computation Over Multiple-Access ChannelsIEEE Transactions on Information Theory, 2007