So sánh phương pháp

	Học tăng cường bán giám sát với ít mẫu (Semi-supervised Few-shot Learning)	Transfer Learning
Lĩnh vực	Học máy	Học máy
Họ	Machine learning	Machine learning
Năm ra đời	2018	2010 (formalized); 1990s (early roots)
Người khởi xướng	Ren, M. et al. (ICLR 2018); builds on Finn et al. (MAML, 2017)	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Loại	Meta-learning with unlabeled auxiliary data	Learning paradigm
Công trình gốc	Ren, M., Triantafillou, E., Ravi, S., Snell, J., Swersky, K., Tenenbaum, J. B., Larochelle, H., & Zemel, R. S. (2018). Meta-learning for semi-supervised few-shot classification. In International Conference on Learning Representations (ICLR 2018).	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Tên gọi khác	SS-FSL, semi-supervised meta-learning, few-shot learning with unlabeled data, low-label few-shot learning	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Liên quan	4	3
Tóm tắt	Semi-supervised Few-shot Learning (SS-FSL) trains models to classify new classes from only a handful of labeled examples per class, while simultaneously leveraging a pool of unlabeled data to enrich class representations. By combining meta-learning episodes with soft pseudo-label assignment for unlabeled samples, it achieves notably higher accuracy than purely supervised few-shot methods when abundant unlabeled data is available.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.