Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards

Yekun Chai, Shuohuan Wang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

Abstract
Derivative-free prompt learning has emerged as a lightweight alternative to prompt tuning, which only requires model inference to optimize the prompts. However, existing work did not take full advantage of the over-parameterized characteristics of large pre-trained language models (PLMs). In this paper, we propose Clip-Tuning, a simple yet effective method that adopts diverse frozen “thinned” networks of PLMs to obtain *a mixture of rewards* and thus advance the derivative-free prompt learning. The thinned networks consist of all the hidden units that survive a stationary dropout strategy, whose inference predictions reflect an ensemble of partial views over prompted training samples. Our method outperforms previous gradient-free prompt learning methods and achieves parity with gradient-based counterparts on seven language understanding benchmarks under few-shot settings.
Anthology ID:
2022.findings-emnlp.8
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
108–117
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.8
DOI:
10.18653/v1/2022.findings-emnlp.8
Bibkey:
Cite (ACL):
Yekun Chai, Shuohuan Wang, Yu Sun, Hao Tian, Hua Wu, and Haifeng Wang. 2022. Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 108–117, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards (Chai et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2022.findings-emnlp.8.pdf
PDF Search