SOURCE-LINKED INTELLIGENCE

Adaptive Determinantal Client Scheduling in Federated Learning

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Scheduling clients for model training is critical in federated learning due to both data and system heterogeneity. Most previous works focus on the quality of the scheduled clients to achieve faster convergence, shorter wall-clock convergence time, or better average model performance. They rarely consider the diversity of clients, which is important to counter heterogeneity and improve performance for the worst-off clients. In this work, we advocate the use of determinantal point processes (DPPs) to model and enhance the diversity in client scheduling. We first design the kernel matrices of DP

Read original source ↗ Open in workspace

recordType

paper

region

Global