AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language Models
Yue Yu, Lingkai Kong, Jieyu Zhang, Rongzhi Zhang, Chao Zhang
Abstract
Although fine-tuning pre-trained language models (PLMs) renders strong performance in many NLP tasks, it relies on excessive labeled data. Recently, researchers have resorted to active fine-tuning for enhancing the label efficiency of PLM fine-tuning, but existing methods of this type usually ignore the potential of unlabeled data. We develop AcTune, a new framework that improves the label efficiency of active PLM fine-tuning by unleashing the power of unlabeled data via self-training. AcTune switches between data annotation and model self-training based on uncertainty: the unlabeled samples of high-uncertainty are selected for annotation, while the ones from low-uncertainty regions are used for model self-training. Additionally, we design (1) a region-aware sampling strategy to avoid redundant samples when querying annotations and (2) a momentum-based memory bank to dynamically aggregate the model’s pseudo labels to suppress label noise in self-training. Experiments on 6 text classification datasets show that AcTune outperforms the strongest active learning and self-training baselines and improves the label efficiency of PLM fine-tuning by 56.2% on average. Our implementation is available at https://github.com/yueyu1030/actune.- Anthology ID:
- 2022.naacl-main.102
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1422–1436
- Language:
- URL:
- https://aclanthology.org/2022.naacl-main.102
- DOI:
- 10.18653/v1/2022.naacl-main.102
- Cite (ACL):
- Yue Yu, Lingkai Kong, Jieyu Zhang, Rongzhi Zhang, and Chao Zhang. 2022. AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language Models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1422–1436, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language Models (Yu et al., NAACL 2022)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2022.naacl-main.102.pdf
- Code
- yueyu1030/actune
- Data
- AG News, PubMed RCT, SST, SST-2, Wrench