Сравнение методов

	Метрическое обучение	Самообучение с учителем
Область	Машинное обучение	Машинное обучение
Семейство	Machine learning	Machine learning
Год появления	2003 (foundational); refined 2009 (LMNN)	2018–2020
Автор метода	Xing, E. P.; Jordan, M. I.; Russell, S.; Ng, A. Y.	LeCun, Y. and community (formalized ~2018–2020)
Тип	Representation learning / supervised distance optimization	Representation learning paradigm
Основополагающий источник	Xing, E. P., Jordan, M. I., Russell, S., & Ng, A. Y. (2003). Distance metric learning with application to clustering with side-information. In Advances in Neural Information Processing Systems (NIPS), 16, 505–512.	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/
Другие названия	Distance Metric Learning, Similarity Learning, DML, Representation Learning via Distance	SSL, self-supervised pre-training, pretext-task learning, unsupervised representation learning
Связанные	5	3
Сводка	Metric learning is a machine-learning framework that trains a distance or similarity function from data so that semantically similar examples end up close together in the learned space while dissimilar examples are pushed apart. Unlike fixed distances such as Euclidean, the learned metric adapts to the structure of the task, making downstream classifiers, clusterers, and retrieval systems significantly more accurate.	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.