方法对比

	贝叶斯少样本学习	贝叶斯迁移学习
领域	机器学习	机器学习
方法族	Machine learning	Machine learning
起源年份	2018-2019	2006–2010
提出者	Gordon et al.; Finn, Xu & Levine	Raina, R.; Ng, A. Y.; Koller, D. (and subsequent community)
类型	Probabilistic meta-learning	Probabilistic transfer / domain adaptation framework
开创性文献	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).	Raina, R., Ng, A. Y., & Koller, D. (2006). Constructing informative priors using transfer learning. In Proceedings of the 23rd International Conference on Machine Learning (ICML), pp. 713–720. ACM.
别名	Bayesian meta-learning, probabilistic few-shot learning, amortized Bayesian few-shot learning, Bayesian FSL	BTL, Bayesian domain adaptation, probabilistic transfer learning, Bayesian knowledge transfer
相关	5	4
摘要	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.	Bayesian Transfer Learning is a probabilistic framework that uses knowledge from a data-rich source domain to construct informative priors for a model trained on a data-scarce target domain. By encoding source-domain knowledge as prior distributions over parameters, the framework lets the model generalize well on the target task even with very limited labeled examples.