Cluster-Based Client Selection for Dependent Multi-Task Federated Learning in Edge Computing
This addresses efficiency challenges in Federated Learning for edge computing environments with dependent tasks, representing an incremental improvement over existing methods.
The paper tackles the client selection problem in Federated Learning for mobile edge computing under dependent multi-task settings, proposing CoDa-FL to reduce total time via cluster-based client selection and dependent task assignment, with experiments showing it outperforms benchmarks by achieving faster convergence, lower costs, and higher accuracy.
We study the client selection problem in Federated Learning (FL) within mobile edge computing (MEC) environments, particularly under the dependent multi-task settings, to reduce the total time required to complete various learning tasks. We propose CoDa-FL, a Cluster-oriented and Dependency-aware framework designed to reduce the total required time via cluster-based client selection and dependent task assignment. Our approach considers Earth Mover's Distance (EMD) for client clustering based on their local data distributions to lower computational cost and improve communication efficiency. We derive a direct and explicit relationship between intra-cluster EMD and the number of training rounds required for convergence, thereby simplifying the otherwise complex process of obtaining the optimal solution. Additionally, we incorporate a directed acyclic graph-based task scheduling mechanism to effectively manage task dependencies. Through numerical experiments, we validate that our proposed CoDa-FL outperforms existing benchmarks by achieving faster convergence, lower communication and computational costs, and higher learning accuracy under heterogeneous MEC settings.