Distributed client selection with multi-objective in federated learning assisted Internet of Vehicles
This addresses the cost problem for federated learning in the Internet of Vehicles, but it is incremental as it builds on existing client selection methods.
The paper tackles the high cost of maintaining active states for all vehicles in federated learning for the Internet of Vehicles by proposing a distributed client selection scheme that uses fuzzy logic to evaluate clients based on sample quantity, throughput, computational capability, and dataset quality. Simulation results show it approximates centralized selection in accuracy and significantly reduces communication overhead.
Federated learning is an emerging distributed machine learning framework in the Internet of Vehicles (IoV). In IoV, millions of vehicles are willing to train the model to share their knowledge. Maintaining an active state means the participants must update their state to the FL server in a fixed interval and participate to next round. However, the cost by maintaining an active state is very large when there are a huge number of participating vehicles. In this paper, we proposed a distributed client selection scheme to reduce the cost of maintaining the active state for all participants. The clients with the highest evaluation are elected among the neighbours. In the evaluator, four variables are considered including sample quantity, throughput available, computational capability and the quality of the local dataset. We adopted fuzzy logic as the evaluator since the closed-form solution over four variables does not exist. Extensive simulation results show our proposal approximates the centralized client selection in terms of accuracy and can significantly reduce the communication overhead.