Prototype-wise momentum-based federated contrast learning

Federated learning (FL) has gained significant attention for enabling privacy preservation and knowledge sharing by transmitting model parameters from clients to a central server. However, with increasing network scale and limited bandwidth, uploading complete model parameters has become increasingl...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Yong Zhang, Jingrui Zhang, Yanjie Dong, Feng Liang, Aohan Li, Xiping Hu
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	KeAi Communications Co., Ltd. 2025-11-01
Цуврал:	Journal of Information and Intelligence
Нөхцлүүд:	Federated learning Prototype contrastive loss Momentum contrast
Онлайн хандалт:	http://www.sciencedirect.com/science/article/pii/S294971592500040X
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!