Abstract
Recently, a series of works have looked into further improving the adapter-based tuning by manually designing better adapter architectures. Understandably, these manually designed solutions are sub-optimal. In this work, we propose the Learned Adapter framework to automatically learn the optimal adapter architectures for better task adaptation of pre-trained models (PTMs). First, we construct a unified search space for adapter architecture designs. In terms of the optimization method on the search space, we propose a simple-yet-effective method, GDNAS for better architecture optimization. Extensive experiments show that our Learned Adapter framework can outperform the previous parameter-efficient tuning (PETuning) baselines while tuning comparable or fewer parameters. Moreover: (a) the learned adapter architectures are explainable and transferable across tasks. (b) We demonstrate that our architecture search space design is valid.- Anthology ID:
- 2023.findings-acl.468
- 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:
- 7420–7437
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.468
- DOI:
- 10.18653/v1/2023.findings-acl.468
- Cite (ACL):
- Yuming Zhang, Peng Wang, Ming Tan, and Wei Zhu. 2023. Learned Adapters Are Better Than Manually Designed Adapters. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7420–7437, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Learned Adapters Are Better Than Manually Designed Adapters (Zhang et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2023.findings-acl.468.pdf