Jul, 2023
DynamicFL：平衡通信动态和客户端操作的联邦学习
DynamicFL: Balancing Communication Dynamics and Client Manipulation for Federated Learning
Bocheng Chen, Nikolay Ivanov, Guangjing Wang, Qiben Yan
TL;DRFederated Learning aims to train a global model by utilizing decentralized data, but the highly dynamic networks of edge devices can cause delays and degrade the efficiency of the training process. To address this, DynamicFL is proposed as a novel framework that considers communication dynamics, data quality, and client selection strategies to improve system performance and achieve better model accuracy.