方法对比

	Self-supervised Federated Learning	半监督学习
领域	机器学习	机器学习
方法族	Machine learning	Machine learning
起源年份	2021–2022	1970s–2006 (formalized)
提出者	McMahan et al. (federated); Zhuang et al. and others (federated SSL combination)	Vapnik, V. N. and others (community of researchers, 1970s–2000s)
类型	Federated self-supervised pretraining paradigm	Learning paradigm
开创性文献	Zhuang, W., Wen, Y., & Zhang, S. (2021). Divergence-aware Federated Self-Supervised Learning. In International Conference on Learning Representations (ICLR 2022).	Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9
别名	FedSSL, Federated Self-supervised Learning, Federated Contrastive Learning, Self-supervised Federated Pretraining	SSL, semi-supervised machine learning, transductive learning, label-efficient learning
相关	5	5
摘要	Self-supervised Federated Learning combines federated training — where data never leaves local devices — with self-supervised pretext tasks such as contrastive learning or masked prediction. Clients learn general-purpose representations from their own unlabeled data and share only model updates, not raw data, with a central server that aggregates them into a global encoder.	Semi-supervised learning (SSL) is a machine learning paradigm that trains models using a small set of labeled examples together with a much larger pool of unlabeled data. By leveraging the structure inherent in unlabeled data, SSL achieves accuracy closer to fully supervised models while requiring far fewer costly manual labels — making it practical when labeling is expensive, slow, or resource-constrained.