手法を比較

	自己教師あり連合学習	Few-shot Learning
分野	機械学習	機械学習
系統	Machine learning	Machine learning
提唱年	2021–2022	2011–2017
提唱者	McMahan et al. (federated); Zhuang et al. and others (federated SSL combination)	Lake, B. M.; Vinyals, O.; Finn, C. et al.
種類	Federated self-supervised pretraining paradigm	Meta-learning / low-data learning paradigm
原典	Zhuang, W., Wen, Y., & Zhang, S. (2021). Divergence-aware Federated Self-Supervised Learning. In International Conference on Learning Representations (ICLR 2022).	Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., & Kavukcuoglu, K. (2016). Matching Networks for One Shot Learning. Advances in Neural Information Processing Systems (NeurIPS), 29.
別名	FedSSL, Federated Self-supervised Learning, Federated Contrastive Learning, Self-supervised Federated Pretraining	FSL, low-shot learning, k-shot learning, meta-learning for few examples
関連	5	4
概要	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.	Few-shot learning is a machine learning paradigm that trains models to recognize new classes or solve new tasks from only a handful of labeled examples — typically one to five — by leveraging prior knowledge acquired from a large, related training distribution. It is especially relevant in domains where labeling is expensive, scarce, or structurally limited.