Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm
Shaoyi Huang, Dongkuan Xu, Ian Yen, Yijue Wang, Sung-En Chang, Bingbing Li, Shiyang Chen, Mimi Xie, Sanguthevar Rajasekaran, Hang Liu, Caiwen Ding
Abstract
Conventional wisdom in pruning Transformer-based language models is that pruning reduces the model expressiveness and thus is more likely to underfit rather than overfit. However, under the trending pretrain-and-finetune paradigm, we postulate a counter-traditional hypothesis, that is: pruning increases the risk of overfitting when performed at the fine-tuning phase. In this paper, we aim to address the overfitting problem and improve pruning performance via progressive knowledge distillation with error-bound properties. We show for the first time that reducing the risk of overfitting can help the effectiveness of pruning under the pretrain-and-finetune paradigm. Ablation studies and experiments on the GLUE benchmark show that our method outperforms the leading competitors across different tasks.- Anthology ID:
- 2022.acl-long.16
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 190–200
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.16
- DOI:
- 10.18653/v1/2022.acl-long.16
- Cite (ACL):
- Shaoyi Huang, Dongkuan Xu, Ian Yen, Yijue Wang, Sung-En Chang, Bingbing Li, Shiyang Chen, Mimi Xie, Sanguthevar Rajasekaran, Hang Liu, and Caiwen Ding. 2022. Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 190–200, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm (Huang et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2022.acl-long.16.pdf
- Data
- GLUE, QNLI