Self-Training with Differentiable Teacher
Simiao Zuo, Yue Yu, Chen Liang, Haoming Jiang, Siawpeng Er, Chao Zhang, Tuo Zhao, Hongyuan Zha
Abstract
Self-training achieves enormous success in various semi-supervised and weakly-supervised learning tasks. The method can be interpreted as a teacher-student framework, where the teacher generates pseudo-labels, and the student makes predictions. The two models are updated alternatingly. However, such a straightforward alternating update rule leads to training instability. This is because a small change in the teacher may result in a significant change in the student. To address this issue, we propose DRIFT, short for differentiable self-training, that treats teacher-student as a Stackelberg game. In this game, a leader is always in a more advantageous position than a follower. In self-training, the student contributes to the prediction performance, and the teacher controls the training process by generating pseudo-labels. Therefore, we treat the student as the leader and the teacher as the follower. The leader procures its advantage by acknowledging the follower’s strategy, which involves differentiable pseudo-labels and differentiable sample weights. Consequently, the leader-follower interaction can be effectively captured via Stackelberg gradient, obtained by differentiating the follower’s strategy. Experimental results on semi- and weakly-supervised classification and named entity recognition tasks show that our model outperforms existing approaches by large margins.- Anthology ID:
- 2022.findings-naacl.70
- Volume:
- Findings of the Association for Computational Linguistics: NAACL 2022
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 933–949
- Language:
- URL:
- https://aclanthology.org/2022.findings-naacl.70
- DOI:
- 10.18653/v1/2022.findings-naacl.70
- Cite (ACL):
- Simiao Zuo, Yue Yu, Chen Liang, Haoming Jiang, Siawpeng Er, Chao Zhang, Tuo Zhao, and Hongyuan Zha. 2022. Self-Training with Differentiable Teacher. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 933–949, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- Self-Training with Differentiable Teacher (Zuo et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.findings-naacl.70.pdf
- Data
- AG News, BC5CDR, IMDb Movie Reviews