Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning

Zhen-Ru Zhang, Chuanqi Tan, Haiyang Xu, Chengyu Wang, Jun Huang, Songfang Huang


Abstract
Fine-tuning large pre-trained language models on various downstream tasks with whole parameters is prohibitively expensive. Hence, Parameter-efficient fine-tuning has attracted attention that only optimizes a few task-specific parameters with the frozen pre-trained model. In this work, we focus on prefix tuning, which only optimizes continuous prefix vectors (i.e. pseudo tokens) inserted into Transformer layers. Based on the observation that the learned syntax and semantics representation varies a lot at different layers, we argue that the adaptive prefix will be further tailored to each layer than the fixed one, enabling the fine-tuning more effective and efficient. Thus, we propose Adaptive Prefix Tuning (APT) to adjust the prefix in terms of both fine-grained token level and coarse-grained layer level with a gate mechanism. Experiments on the SuperGLUE and NER datasets show the effectiveness of APT. In addition, taking the gate as a probing, we validate the efficiency and effectiveness of the variable prefix.
Anthology ID:
2023.acl-short.107
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1239–1248
Language:
URL:
https://aclanthology.org/2023.acl-short.107
DOI:
10.18653/v1/2023.acl-short.107
Bibkey:
Cite (ACL):
Zhen-Ru Zhang, Chuanqi Tan, Haiyang Xu, Chengyu Wang, Jun Huang, and Songfang Huang. 2023. Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1239–1248, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning (Zhang et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.acl-short.107.pdf
Video:
 https://preview.aclanthology.org/naacl24-info/2023.acl-short.107.mp4