Small Pre-trained Language Models Can be Fine-tuned as Large Models via Over-Parameterization

Ze-Feng Gao, Kun Zhou, Peiyu Liu, Wayne Xin Zhao, Ji-Rong Wen


Abstract
By scaling the model size, large pre-trained language models (PLMs) have shown remarkable performance in various natural language processing tasks, mostly outperforming small PLMs by a large margin. However, due to the high computational cost, the huge number of parameters also restricts the applicability of large PLMs in real-world systems. In this paper, we focus on scaling up the parameters of PLMs only during fine-tuning, to benefit from the over-parameterization, while without increasing the inference latency. Given a relatively small PLM, we over-parameterize it by employing a matrix product operator, an efficient and almost lossless decomposition method to factorize its contained parameter matrices into a set of higher-dimensional tensors.Considering the efficiency, we further propose both static and dynamic strategies to select the most important parameter matrices for over-parameterization.Extensive experiments have demonstrated that our approach can significantly boost the fine-tuning performance of small PLMs and even help small PLMs outperform parameterized larger ones.Our code is publicly available at https://github.com/zfgao66/OPF.
Anthology ID:
2023.acl-long.212
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long 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:
3819–3834
Language:
URL:
https://aclanthology.org/2023.acl-long.212
DOI:
10.18653/v1/2023.acl-long.212
Bibkey:
Cite (ACL):
Ze-Feng Gao, Kun Zhou, Peiyu Liu, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Small Pre-trained Language Models Can be Fine-tuned as Large Models via Over-Parameterization. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3819–3834, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Small Pre-trained Language Models Can be Fine-tuned as Large Models via Over-Parameterization (Gao et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.212.pdf
Video:
 https://aclanthology.org/2023.acl-long.212.mp4