UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning

Yuning Mao, Lambert Mathias, Rui Hou, Amjad Almahairi, Hao Ma, Jiawei Han, Scott Yih, Madian Khabsa


Abstract
Recent parameter-efficient language model tuning (PELT) methods manage to match the performance of fine-tuning with much fewer trainable parameters and perform especially well when training data is limited. However, different PELT methods may perform rather differently on the same task, making it nontrivial to select the most appropriate method for a specific task, especially considering the fast-growing number of new PELT methods and tasks. In light of model diversity and the difficulty of model selection, we propose a unified framework, UniPELT, which incorporates different PELT methods as submodules and learns to activate the ones that best suit the current data or task setup via gating mechanism. On the GLUE benchmark, UniPELT consistently achieves 1 4% gains compared to the best individual PELT method that it incorporates and even outperforms fine-tuning under different setups. Moreover, UniPELT generally surpasses the upper bound that takes the best performance of all its submodules used individually on each task, indicating that a mixture of multiple PELT methods may be inherently more effective than single methods.
Anthology ID:
2022.acl-long.433
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:
6253–6264
Language:
URL:
https://aclanthology.org/2022.acl-long.433
DOI:
10.18653/v1/2022.acl-long.433
Bibkey:
Cite (ACL):
Yuning Mao, Lambert Mathias, Rui Hou, Amjad Almahairi, Hao Ma, Jiawei Han, Scott Yih, and Madian Khabsa. 2022. UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6253–6264, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning (Mao et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2022.acl-long.433.pdf
Code
 morningmoni/unipelt
Data
GLUEQNLI