手法を比較

	ベイズ距離学習	Few-shot Learning
分野	機械学習	機械学習
系統	Machine learning	Machine learning
提唱年	2010s	2011–2017
提唱者	Multiple (Xing et al. 2002; Weinberger & Saul 2009; probabilistic extensions by various authors ~2010s)	Lake, B. M.; Vinyals, O.; Finn, C. et al.
種類	Probabilistic distance metric learning	Meta-learning / low-data learning paradigm
原典	Weinberger, K. Q., & Saul, L. K. (2009). Distance metric learning for large margin nearest neighbor classification. Journal of Machine Learning Research, 10, 207–244.	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.
別名	BML, probabilistic metric learning, Bayesian distance metric learning, Bayesian similarity learning	FSL, low-shot learning, k-shot learning, meta-learning for few examples
関連	5	4
概要	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.	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.