Making Pretrained Language Models Good Long-tailed Learners

Chen Zhang, Lei Ren, Jingang Wang, Wei Wu, Dawei Song


Abstract
Prompt-tuning has shown appealing performance in few-shot classification by virtue of its capability in effectively exploiting pre-trained knowledge. This motivates us to check the hypothesis that prompt-tuning is also a promising choice for long-tailed classification, since the tail classes are intuitively few-shot ones. To achieve this aim, we conduct empirical studies to examine the hypothesis. The results demonstrate that prompt-tuning makes pretrained language models at least good long-tailed learners. For intuitions on why prompt-tuning can achieve good performance in long-tailed classification, we carry out in-depth analyses by progressively bridging the gap between prompt-tuning and commonly used finetuning. The summary is that the classifier structure and parameterization form the key to making good long-tailed learners, in comparison with the less important input structure. Finally, we verify the applicability of our finding to few-shot classification.
Anthology ID:
2022.emnlp-main.217
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:
3298–3312
Language:
URL:
https://aclanthology.org/2022.emnlp-main.217
DOI:
Bibkey:
Cite (ACL):
Chen Zhang, Lei Ren, Jingang Wang, Wei Wu, and Dawei Song. 2022. Making Pretrained Language Models Good Long-tailed Learners. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3298–3312, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Making Pretrained Language Models Good Long-tailed Learners (Zhang et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-ingestion/2022.emnlp-main.217.pdf