Võrdle meetodeid
Vaata valitud meetodeid kõrvuti; erinevad read on esile tõstetud.
| Pooltugevdatud GAN× | Poolitatud-järelevalvega BERT-põhine klassifitseerimine× | |
|---|---|---|
| Valdkond | Süvaõpe | Süvaõpe |
| Perekond | Machine learning | Machine learning |
| Tekkeaasta≠ | 2016 | 2019–2020 |
| Looja≠ | Odena, A.; Salimans, T. et al. | Multiple groups (Xie et al.; Chen et al.; Devlin et al. for BERT base) |
| Tüüp≠ | Semi-supervised generative model | Semi-supervised fine-tuning of pre-trained transformer |
| Algallikas≠ | 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. link ↗ | 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. link ↗ |
| Rööpnimetused | 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 |
| Seotud≠ | 5 | 6 |
| Kokkuvõte≠ | 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. |
| ScholarGateAndmestik ↗ |
|
|