non-iid-data

本文提出FedLBW，一种联邦学习聚合策略，该策略使用验证损失的倒数而非数据集大小来加权客户端更新，提高了在无线网络中应对非独立同分布数据和客户端掉线时的准确性和鲁棒性。

Presents DG-FedReuse, a federated learning mechanism that reuses age-decayed cached client updates under a proxy-gradient threshold to reduce uplink communication, achieving significant modeled savings with minimal accuracy loss on image classification benchmarks.