Comparer des méthodes

	Apprentissage métrique d'ensemble	Apprentissage à peu d'exemples
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2000s–2010s	2011–2017
Auteur d'origine	Multiple contributors (Weinberger, Saul, et al.)	Lake, B. M.; Vinyals, O.; Finn, C. et al.
Type	Ensemble of learned distance metrics	Meta-learning / low-data learning paradigm
Source fondatrice	Wang, J., Kalousis, A., & Woznica, A. (2012). Parametric local metric learning for nearest neighbor classification. Advances in Neural Information Processing Systems, 25.	Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., & Kavukcuoglu, K. (2016). Matching Networks for One Shot Learning. Advances in Neural Information Processing Systems (NeurIPS), 29.
Alias	EML, ensemble distance metric learning, multiple metric fusion, combined metric learning	FSL, low-shot learning, k-shot learning, meta-learning for few examples
Apparentées	5	4
Résumé	Ensemble Metric Learning trains multiple distance metric learners — each on a different data view, feature subspace, or with a different objective — and combines the resulting metrics to produce a single, more robust similarity function. Combining diverse metrics reduces the variance of any individual metric and improves performance in tasks such as nearest-neighbor classification, retrieval, and few-shot learning.	Few-shot learning is a machine learning paradigm that trains models to recognize new classes or solve new tasks from only a handful of labeled examples — typically one to five — by leveraging prior knowledge acquired from a large, related training distribution. It is especially relevant in domains where labeling is expensive, scarce, or structurally limited.