ESFL: Efficient Split Federated Learning over Resource-Constrained Heterogeneous Wireless Devices
This addresses the challenge of resource utilization in federated learning for wireless devices, but it is incremental as it builds on existing split federated learning frameworks.
The paper tackles the problem of efficiently training machine learning models across resource-constrained heterogeneous wireless devices by proposing ESFL, an algorithm that splits the model between devices and a central server to optimize resource allocation, resulting in significantly increased efficiency compared to standard federated learning, split learning, and splitfed learning as validated by simulations.
Federated learning (FL) allows multiple parties (distributed devices) to train a machine learning model without sharing raw data. How to effectively and efficiently utilize the resources on devices and the central server is a highly interesting yet challenging problem. In this paper, we propose an efficient split federated learning algorithm (ESFL) to take full advantage of the powerful computing capabilities at a central server under a split federated learning framework with heterogeneous end devices (EDs). By splitting the model into different submodels between the server and EDs, our approach jointly optimizes user-side workload and server-side computing resource allocation by considering users' heterogeneity. We formulate the whole optimization problem as a mixed-integer non-linear program, which is an NP-hard problem, and develop an iterative approach to obtain an approximate solution efficiently. Extensive simulations have been conducted to validate the significantly increased efficiency of our ESFL approach compared with standard federated learning, split learning, and splitfed learning.