摘要
We investigate energy-efficient federated learning (FL) in computation and communication resource-constrained edge intelligence networks using model compression. An edge device selection strategy is designed to select appropriate edge devices for participating in FL at the beginning of each training iteration. An optimization problem is then formulated to jointly optimize the pruning ratio, CPU frequency, uplink power, and bandwidth allocation for the selected edge devices. Due to the non-convexity of the optimization problem, it is decomposed into three subproblems, and closed-form solutions or efficient algorithms are developed for each subproblem. Based on these solutions, an alternating optimization algorithm is constructed to solve the original problem. Simulation results show that the proposed scheme outperforms baseline schemes in improving the energy efficiency of FL.
学科与关键词
- Energy Efficient Federated Learning Over Heterogeneous Mobile Devices via Joint Design of Weight Quantization and Wireless TransmissionChen, Rui; Li, Liang; Xue, Kaiping; Zhang, Chi; Pan, Miao*; Fang, YuguangIEEE Transactions on Mobile Computing, 2023, 22(12): 7451-7465.被引 2
- User Selection Aware Joint Radio-and-Computing Resource Allocation for Federated Edge LearningZuo, Yunjie*; Liu, Yuan12th International Conference on Wireless Communications and Signal Processing (WCSP), Nanjing, PEOPLES R CHINA, 2020-10-21 To 2020-10-23.被引 2
- Joint Gradient Sparsification and Device Scheduling for Federated LearningLin, Xiaohan; Liu, Yuan*; Chen, Fangjiong*; Ge, Xiaohu; Huang, YangIEEE TRANSACTIONS ON GREEN COMMUNICATIONS AND NETWORKING, 2023, 7(3): 1407-1419.被引 1
