Revisiting Parameter-Efficient Tuning: Are We Really There Yet?

Guanzheng Chen, Fangyu Liu, Zaiqiao Meng, Shangsong Liang


Abstract
Parameter-Efficient Tuning (PETuning) methods have been deemed by many as the new paradigm for using pretrained language models (PLMs). By tuning just a fraction amount of parameters comparing to full model finetuning, PETuning methods claim to have achieved performance on par with or even better than finetuning. In this work, we take a step back and re-examine these PETuning methods by conducting the first comprehensive investigation into the training and evaluation of them. We found the problematic validation and testing practice in current studies, when accompanied by the instability nature of PETuning methods, has led to unreliable conclusions. When being compared under a truly fair evaluation protocol, PETuning cannot yield consistently competitive performance while finetuning remains to be the best-performing method in medium- and high-resource settings. We delve deeper into the cause of the instability and observed that the number of trainable parameters and training iterations are two main factors: reducing trainable parameters and prolonging training iterations may lead to higher stability in PETuning methods.
Anthology ID:
2022.emnlp-main.168
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2612–2626
Language:
URL:
https://aclanthology.org/2022.emnlp-main.168
DOI:
Bibkey:
Cite (ACL):
Guanzheng Chen, Fangyu Liu, Zaiqiao Meng, and Shangsong Liang. 2022. Revisiting Parameter-Efficient Tuning: Are We Really There Yet?. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 2612–2626, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Revisiting Parameter-Efficient Tuning: Are We Really There Yet? (Chen et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.emnlp-main.168.pdf