HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks

Zhengkun Zhang, Wenya Guo, Xiaojun Meng, Yasheng Wang, Yadao Wang, Xin Jiang, Qun Liu, Zhenglu Yang


Abstract
With the scale and capacity of pretrained models growing rapidly, parameter-efficient language model tuning has emerged as a popular paradigm for solving various NLP and Vision-and-Language (V&L) tasks. In this paper, we design a unified parameter-efficient multitask learning framework that works effectively on both NLP and V&L tasks. In particular, we use a shared hypernetwork that takes trainable hyper-embeddings and visual modality as input, and outputs weights for different modules in a pretrained language model, such as the parameters inserted into multi-head attention blocks (i.e., prefix-tuning) and feed-forward blocks (i.e., adapter-tuning.). Our proposed framework adds fewer trainable parameters in multi-task learning while achieving superior performances and transfer ability compared to state-of-the-art methods. Empirical results on the GLUE benchmark and multiple V&L tasks confirm the effectiveness of our framework.
Anthology ID:
2023.findings-acl.725
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11442–11453
Language:
URL:
https://aclanthology.org/2023.findings-acl.725
DOI:
10.18653/v1/2023.findings-acl.725
Bibkey:
Cite (ACL):
Zhengkun Zhang, Wenya Guo, Xiaojun Meng, Yasheng Wang, Yadao Wang, Xin Jiang, Qun Liu, and Zhenglu Yang. 2023. HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11442–11453, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks (Zhang et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.findings-acl.725.pdf