Сравнение методов

	Самообучающиеся k-ближайших соседей	Метрическое обучение
Область	Машинное обучение	Машинное обучение
Семейство	Machine learning	Machine learning
Год появления	2018–2020	2003 (foundational); refined 2009 (LMNN)
Автор метода	Wu, Z. et al. / Chen, T. et al.	Xing, E. P.; Jordan, M. I.; Russell, S.; Ng, A. Y.
Тип	Self-supervised + non-parametric classifier	Representation learning / supervised distance optimization
Основополагающий источник	Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119, 1597–1607.	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.
Другие названия	SSL-kNN, self-supervised kNN classifier, kNN evaluation probe, nearest-neighbor self-supervised classifier	Distance Metric Learning, Similarity Learning, DML, Representation Learning via Distance
Связанные	4	5
Сводка	Self-supervised K-nearest neighbors (SSL-kNN) combines representation learning without labels with a non-parametric k-NN classifier. A neural encoder is first trained via a self-supervised objective — such as contrastive or masked prediction — so that semantically similar samples cluster together in the embedding space. A simple k-NN lookup on those embeddings then assigns class labels, serving both as a lightweight probe and as a practical classifier.	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.