Residual Prompt Tuning: improving prompt tuning with residual reparameterization

Anastasiia Razdaibiedina, Yuning Mao, Madian Khabsa, Mike Lewis, Rui Hou, Jimmy Ba, Amjad Almahairi


Abstract
Prompt tuning is one of the successful approaches for parameter-efficient tuning of pre-trained language models. Despite being arguably the most parameter-efficient (tuned soft prompts constitute <0.1% of total parameters), it typically performs worse than other efficient tuning methods and is quite sensitive to hyper-parameters. In this work, we introduce Residual Prompt Tuning - a simple and efficient method that significantly improves the performance and stability of prompt tuning. We propose to reparameterize soft prompt embeddings using a shallow network with a residual connection. Our experiments show that Residual Prompt Tuning significantly outperforms prompt tuning across T5-Large, T5-Base and BERT-Base models. Notably, our method reaches +7 points improvement over prompt tuning on SuperGLUE benchmark with T5-Base model and allows to reduce the prompt length by 10 times without hurting performance. In addition, we show that our approach is robust to the choice of learning rate and prompt initialization, and is effective in few-shot settings.
Anthology ID:
2023.findings-acl.421
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6740–6757
Language:
URL:
https://aclanthology.org/2023.findings-acl.421
DOI:
10.18653/v1/2023.findings-acl.421
Bibkey:
Cite (ACL):
Anastasiia Razdaibiedina, Yuning Mao, Madian Khabsa, Mike Lewis, Rui Hou, Jimmy Ba, and Amjad Almahairi. 2023. Residual Prompt Tuning: improving prompt tuning with residual reparameterization. In Findings of the Association for Computational Linguistics: ACL 2023, pages 6740–6757, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Residual Prompt Tuning: improving prompt tuning with residual reparameterization (Razdaibiedina et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.421.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.421.mp4