方法对比

	半监督式 Transformer	微调Transformer
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2018–2019	2017–2019
提出者	Devlin, J. et al. (BERT); broader SSL-Transformer paradigm community	Vaswani et al. (architecture); fine-tuning paradigm popularised by Howard & Ruder, Devlin et al.
类型	Semi-supervised deep learning	Transfer learning / supervised fine-tuning
开创性文献	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.	Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
别名	semi-supervised transformer model, SSL transformer, transformer with self-supervised pre-training, semi-supervised attention model	Transformer fine-tuning, pre-trained transformer fine-tuning, task-adaptive transformer, downstream-tuned transformer
相关	5	4
摘要	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.	Fine-tuning a Transformer adapts a large pre-trained model — such as BERT, GPT, or ViT — to a specific downstream task by continuing gradient-based training on a labelled target dataset. This two-stage paradigm (pre-train then fine-tune) consistently achieves state-of-the-art results across NLP and computer vision tasks with far less task-specific data than training from scratch.