Comparer des méthodes

	Apprentissage métrique semi-supervisé	Apprentissage par transfert
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2007–2008	2010 (formalized); 1990s (early roots)
Auteur d'origine	Yeung, D.-Y. & Chang, H.; Davis, J. V. & Dhillon, I. S.	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Type	Hybrid supervised/unsupervised distance learning	Learning paradigm
Source fondatrice	Yeung, D.-Y., & Chang, H. (2007). A kernel approach for semi-supervised metric learning. IEEE Transactions on Neural Networks, 18(1), 141–149.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Alias	SSML, semi-supervised distance learning, constrained metric learning, weakly supervised metric learning	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Apparentées	5	3
Résumé	Semi-supervised metric learning learns a task-adapted distance function by combining a small set of labeled pairwise constraints — must-link and cannot-link pairs — with the geometric structure of a much larger pool of unlabeled data. The result is a Mahalanobis-style or kernel-based distance that reflects both supervision and data topology, improving downstream tasks such as nearest-neighbor classification and clustering.	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.