方法对比

	Semi-supervised GAN	半监督式BERT分类
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2016	2019–2020
提出者	Odena, A.; Salimans, T. et al.	Multiple groups (Xie et al.; Chen et al.; Devlin et al. for BERT base)
类型	Semi-supervised generative model	Semi-supervised fine-tuning of pre-trained transformer
开创性文献	Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved Techniques for Training GANs. Advances in Neural Information Processing Systems (NeurIPS), 29.	Xie, Q., Dai, Z., Hovy, E., Luong, T., & Le, Q. (2020). Unsupervised Data Augmentation for Consistency Training. Advances in Neural Information Processing Systems (NeurIPS), 33, 27780–27792.
别名	SGAN, Semi-GAN, semi-supervised generative adversarial network, GAN-based semi-supervised learning	Semi-supervised BERT, BERT SSL Classification, BERT with Unlabeled Data, BERT Semi-supervised Fine-tuning
相关	5	6
摘要	Semi-supervised GAN (SGAN) extends the standard GAN discriminator to simultaneously classify labeled examples into K real classes and detect generated fakes as a (K+1)-th class, letting the generator's synthetic data act as implicit regularization and allowing strong classifiers to be trained with very few labeled examples.	Semi-supervised BERT-based classification fine-tunes a pre-trained BERT encoder on a small pool of labeled text examples while simultaneously leveraging a much larger body of unlabeled text — via consistency training, pseudo-labeling, or data augmentation — to produce high-quality classifiers even when manual annotation is scarce.