Toward Multiple Federated Learning Services Resource Sharing in Mobile Edge Networks
This work is an incremental improvement for federated learning practitioners and researchers working on resource management in mobile edge computing environments.
This paper addresses the challenge of resource sharing for multiple federated learning services in mobile edge networks. It proposes a joint optimization problem, MS-FEDL, to manage CPU and communication resources and hyper-learning rates, aiming to reduce energy consumption and overall learning time. The authors developed both centralized and decentralized algorithms to solve this problem, showing improved performance over a heuristic strategy.
Federated Learning is a new learning scheme for collaborative training a shared prediction model while keeping data locally on participating devices. In this paper, we study a new model of multiple federated learning services at the multi-access edge computing server. Accordingly, the sharing of CPU resources among learning services at each mobile device for the local training process and allocating communication resources among mobile devices for exchanging learning information must be considered. Furthermore, the convergence performance of different learning services depends on the hyper-learning rate parameter that needs to be precisely decided. Towards this end, we propose a joint resource optimization and hyper-learning rate control problem, namely MS-FEDL, regarding the energy consumption of mobile devices and overall learning time. We design a centralized algorithm based on the block coordinate descent method and a decentralized JP-miADMM algorithm for solving the MS-FEDL problem. Different from the centralized approach, the decentralized approach requires many iterations to obtain but it allows each learning service to independently manage the local resource and learning process without revealing the learning service information. Our simulation results demonstrate the convergence performance of our proposed algorithms and the superior performance of our proposed algorithms compared to the heuristic strategy.