To the best of current knowledge, the performance of federated learning predominantly depends on the efficiency of the aggregation server scheme utilized to consolidate model parameters received from distributed local devices. However, in practical scenarios, the global server often faces single-point failures due to four major issues: 1) variations in data distribution settings, such as independent identical distribution (IID) or non-independent identical distribution; 2) communication overhead; 3) limitations in hardware and resource storage availability; and 4) diverse participant participation behaviors. To address the latter concern, limited research has endeavored to establish a correlation between these heterogeneous settings and federated learning performance by analyzing different aspects of participant behavior. Inspired by the absence of a definitive verdict regarding the relationship between the global server and participant behavior, this paper investigates the aspect of participant selection methods and conducts a detailed comparative study among various participant selection methods
Citation
WAFA Bouras ,
Mohamed Benouis ,
Samir Akhrouf ,
brahim.bouderah@univ-msila.dz, ,(2024-05-13), Analysis Study of Participant Selection Methods in Federated Learning,ICEEAC’2024,Setif university