期刊
IEEE TRANSACTIONS ON COMMUNICATIONS
卷 69, 期 9, 页码 5902-5916出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCOMM.2021.3087125
关键词
Collaborative work; Optimization; Computational modeling; Wireless communication; Servers; Quantization (signal); Resource management; Federated learning; artificial intelligence; mobile edge computing; resource management
资金
- Beijing Natural Science Foundation [L182039]
- National Natural Science Foundation of China [61971061]
- National Research Foundation, Singapore
- Infocomm Media Development Authority under its Future Communications Research and Development Programme
- Singapore University of Technology and Design (SUTD) Growth Plan Grant for AI
This paper investigates the optimization design of federated learning in MEC systems, proposing a joint optimization algorithm to address the tradeoff between model accuracy and training cost. The performance of the proposed optimization scheme is evaluated through numerical simulation and experimental results, demonstrating a significant reduction in accuracy loss and cost of federated learning in MEC systems.
The combination of artificial intelligence and mobile edge computing (MEC) is considered as a promising evolution path of the future wireless networks. As a model-level coordination learning paradigm, federated learning can make full use of the distributed computation resource in the MEC systems, which allows the users to keep their private data locally. However, due to the unreliable wireless transmission circumstances and resource constraints in the MEC systems, both the performance and training efficiency of federated learning cannot be guaranteed. To solve this problem, the optimization design of federated learning in the MEC systems is studied in this paper. First, an optimization problem is formulated to manage the tradeoff between model accuracy and training cost. Second, a joint optimization algorithm is designed to optimize the model compression, sample selection, and user selection strategies, which can approach a stationary optimal solution in a computationally efficient way. Finally, the performance of our proposed optimization scheme is evaluated by numerical simulation and experiment results, which show that both the accuracy loss and the cost of federated learning in the MEC systems can be reduced significantly by employing our proposed algorithm.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据