Adaptive Determinantal Client Scheduling in Federated Learning

2026-09-20

AI Summary

本文提出使用确定性点过程来增强联邦学习中客户端调度的多样性，通过自适应确定性客户端调度(ADCS)方法平衡质量和多样性，以应对异质性并改善最差客户端性能。

Abstract

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 DPPs using gradient information and quality scores, which inherently enables a flexible quality-diversity trade-off. Applying fast MAP inference over DPPs, we propose Adaptive Determinantal Client Scheduling (ADCS) in FL. We further quantify the gradient approximation error of ADCS and develop convergence analysis for general biased client selection in FL with non-convex loss functions. We conduct comparative numerical experiments showing that ADCS outperforms state-of-the-art client scheduling algorithms, including both quality-based and diversity-based ones.

Problem

• federated learning
• client scheduling
• diversity
• heterogeneity
• convergence

Innovation

• determinantal point processes
• client scheduling
• federated learning
• gradient information
• quality-diversity trade-off