Comparer des méthodes

	Apprentissage métrique bayésien	Apprentissage bayésien à peu d'exemples
Domaine	Apprentissage automatique	Apprentissage automatique
Famille	Machine learning	Machine learning
Année d'origine	2010s	2018-2019
Auteur d'origine	Multiple (Xing et al. 2002; Weinberger & Saul 2009; probabilistic extensions by various authors ~2010s)	Gordon et al.; Finn, Xu & Levine
Type	Probabilistic distance metric learning	Probabilistic meta-learning
Source fondatrice	Weinberger, K. Q., & Saul, L. K. (2009). Distance metric learning for large margin nearest neighbor classification. Journal of Machine Learning Research, 10, 207–244.	Gordon, J., Bronskill, J., Bauer, M., Nowozin, S. & Turner, R. E. (2019). Meta-Learning Probabilistic Inference for Prediction. International Conference on Learning Representations (ICLR 2019).
Alias	BML, probabilistic metric learning, Bayesian distance metric learning, Bayesian similarity learning	Bayesian meta-learning, probabilistic few-shot learning, amortized Bayesian few-shot learning, Bayesian FSL
Apparentées	5	5
Résumé	Bayesian Metric Learning frames the problem of learning a task-adapted distance function as probabilistic inference. Rather than producing a single optimal metric matrix, it places a prior over metrics, updates it with pairwise similarity or label constraints, and yields a posterior distribution that quantifies uncertainty about which metric best captures the true structure of the data.	Bayesian few-shot learning combines Bayesian inference with meta-learning to enable a model to generalize from as few as one to five labeled examples per class. By treating task-specific parameters as random variables and learning an informative prior across many training tasks, the method produces calibrated uncertainty estimates alongside predictions — a key advantage over deterministic few-shot learners.