方法对比

	半监督变分自编码器	半监督式 Transformer
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2014	2018–2019
提出者	Kingma, D. P.; Mohamed, S.; Rezende, D. J.; Wierstra, D.	Devlin, J. et al. (BERT); broader SSL-Transformer paradigm community
类型	Generative probabilistic model (semi-supervised)	Semi-supervised deep learning
开创性文献	Kingma, D. P., Mohamed, S., Rezende, D. J., & Wierstra, D. (2014). Semi-supervised learning with deep generative models. Advances in Neural Information Processing Systems (NeurIPS), 27, 3581–3589.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, 4171–4186.
别名	Semi-supervised VAE, M2 model, VAE with label propagation, deep generative semi-supervised model	semi-supervised transformer model, SSL transformer, transformer with self-supervised pre-training, semi-supervised attention model
相关	6	5
摘要	The semi-supervised VAE (M2 model) is a deep generative method that jointly learns a latent representation of inputs and a classifier, leveraging both labeled and unlabeled examples in a principled probabilistic framework. Introduced by Kingma et al. in 2014, it allows accurate classification even when labels are scarce by having the generative model explain away unlabeled observations.	Semi-supervised learning with Transformer architectures leverages large quantities of unlabeled data alongside a small labeled set to train powerful sequence models. The dominant pattern — exemplified by BERT — first pre-trains the Transformer on unlabeled data using self-supervised objectives such as masked token prediction, then fine-tunes it on the labeled task. This two-stage approach dramatically reduces the labeled data needed to achieve strong performance.