방법 비교

	자기 지도 학습	준지도 학습	전이 학습
분야	머신러닝	머신러닝	머신러닝
계열	Machine learning	Machine learning	Machine learning
기원 연도	2018–2020	1970s–2006 (formalized)	2010 (formalized); 1990s (early roots)
창시자	LeCun, Y. and community (formalized ~2018–2020)	Vapnik, V. N. and others (community of researchers, 1970s–2000s)	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
유형	Representation learning paradigm	Learning paradigm	Learning paradigm
원전	LeCun, Y. & Misra, I. (2022). Self-supervised learning: The dark matter of intelligence. Meta AI Blog. https://ai.facebook.com/blog/self-supervised-learning-the-dark-matter-of-intelligence/	Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
별칭	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning	SSL, semi-supervised machine learning, transductive learning, label-efficient learning	TL, domain adaptation, fine-tuning, pre-trained model adaptation
관련	3	5	3
요약	Self-supervised learning (SSL) is a machine-learning paradigm that generates its own supervisory signal directly from unlabeled data by defining an auxiliary pretext task — such as predicting masked words, rotating images, or contrasting augmented views — and uses the learned representations as a powerful starting point for downstream tasks with minimal labeled examples.	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.	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.