FedSCS: Client Selection for Federated Learning Under System Heterogeneity and Client Fairness with a Stackelberg Game Approach

Federated learning (FL) embraces the concepts of targeted data gathering and training, and it can reduce many of the systemic privacy costs and hazards associated with traditional machine learning frameworks. However, on the one hand, the wireless communication propagation circumstances and client computation capabilities are not taken into account in traditional synchronous FL algorithms, which causes the time delay in the FL process because the time of each round is determined by the client with the worst performance. On the other hand, the unfairness of client participation in FL may lead to damage to the global accuracy because of the non identically independently distributed (Non-IID) data. In this paper, we propose a Stackelberg game-based FL Client Selection framework, named FedSCS, which considers system heterogeneity, client heterogeneity, and the fairness of client participation to reduce the latency resulting from the heterogeneous communication conditions and computation capabilities among clients with Non-IID data distributions. Specifically, the Stackelberg leader-follower game is first formulated in which the server decides the price of the single quota of participating in the FL process every communication round and the clients decide whether to participate in FL. Then the equilibrium solution of the game is derived and proved. The simulation results verify the effectiveness of the proposed strategy for reducing the time latency of FL processes with heterogeneous clients, i.e., FedAvg, FedOpt, and FedNova.