Extreme Fine-tuning: A Novel and Fast Fine-tuning Approach for Text Classification

Boonnithi Jiaramaneepinit, Thodsaporn Chay-intr, Kotaro Funakoshi, Manabu Okumura


Abstract
Although fine-tuning a pre-trained model with a conventional approach has shown to be effective in various downstream tasks, previous work has used only backpropagation to fine-tune the model, which causes a massive amount of computational resources and time. We propose Extreme Fine-Tuning (EFT), a novel approach for fine-tuning a pre-trained model effectively and efficiently. EFT uses backpropagation for a brief fine-tuning and an iterative extreme learning machine for training a classifier. We applied EFT to four text classification datasets, MELD, IEMOCAP, IMDb, and AG News, and compared its performance with state-of-the-art (SOTA) approaches. The results indicate that EFT noticeably outperformed the other approaches in training-time measurement with comparable model performance. We will release our code at https://github.com/up-33/extreme-fine-tuning.
Anthology ID:
2024.eacl-short.32
Volume:
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
March
Year:
2024
Address:
St. Julian’s, Malta
Editors:
Yvette Graham, Matthew Purver
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
368–379
Language:
URL:
https://aclanthology.org/2024.eacl-short.32
DOI:
Bibkey:
Cite (ACL):
Boonnithi Jiaramaneepinit, Thodsaporn Chay-intr, Kotaro Funakoshi, and Manabu Okumura. 2024. Extreme Fine-tuning: A Novel and Fast Fine-tuning Approach for Text Classification. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 368–379, St. Julian’s, Malta. Association for Computational Linguistics.
Cite (Informal):
Extreme Fine-tuning: A Novel and Fast Fine-tuning Approach for Text Classification (Jiaramaneepinit et al., EACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2024.eacl-short.32.pdf
Video:
 https://preview.aclanthology.org/naacl24-info/2024.eacl-short.32.mp4