DPP-based Client Selection for Federated Learning with Non-IID Data
This addresses efficiency and privacy challenges in federated learning for distributed systems, but it is incremental as it builds on existing sampling techniques.
The paper tackles the communication bottleneck and data heterogeneity in federated learning by proposing a client selection method using determinantal point processes to diversify training datasets per round, resulting in faster convergence and reduced communication overhead compared to baselines.
This paper proposes a client selection (CS) method to tackle the communication bottleneck of federated learning (FL) while concurrently coping with FL's data heterogeneity issue. Specifically, we first analyze the effect of CS in FL and show that FL training can be accelerated by adequately choosing participants to diversify the training dataset in each round of training. Based on this, we leverage data profiling and determinantal point process (DPP) sampling techniques to develop an algorithm termed Federated Learning with DPP-based Participant Selection (FL-DP$^3$S). This algorithm effectively diversifies the participants' datasets in each round of training while preserving their data privacy. We conduct extensive experiments to examine the efficacy of our proposed method. The results show that our scheme attains a faster convergence rate, as well as a smaller communication overhead than several baselines.