Adaptable Adapters

Nafise Moosavi, Quentin Delfosse, Kristian Kersting, Iryna Gurevych


Abstract
State-of-the-art pretrained NLP models contain a hundred million to trillion parameters. Adapters provide a parameter-efficient alternative for the full finetuning in which we can only finetune lightweight neural network layers on top of pretrained weights. Adapter layers are initialized randomly. However, existing work uses the same adapter architecture—i.e., the same adapter layer on top of each layer of the pretrained model—for every dataset, regardless of the properties of the dataset or the amount of available training data. In this work, we introduce adaptable adapters that contain (1) learning different activation functions for different layers and different input data, and (2) a learnable switch to select and only use the beneficial adapter layers. We show that adaptable adapters achieve on-par performances with the standard adapter architecture while using a considerably smaller number of adapter layers. In addition, we show that the selected adapter architecture by adaptable adapters transfers well across different data settings and similar tasks. We propose to use adaptable adapters for designing efficient and effective adapter architectures. The resulting adapters (a) contain about 50% of the learning parameters of the standard adapter and are therefore more efficient at training and inference, and require less storage space, and (b) achieve considerably higher performances in low-data settings.
Anthology ID:
2022.naacl-main.274
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3742–3753
Language:
URL:
https://aclanthology.org/2022.naacl-main.274
DOI:
10.18653/v1/2022.naacl-main.274
Bibkey:
Cite (ACL):
Nafise Moosavi, Quentin Delfosse, Kristian Kersting, and Iryna Gurevych. 2022. Adaptable Adapters. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3742–3753, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Adaptable Adapters (Moosavi et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.274.pdf
Software:
 2022.naacl-main.274.software.zip
Video:
 https://aclanthology.org/2022.naacl-main.274.mp4
Code
 ukplab/adaptable-adapters
Data
CoLAGLUEMRPCMultiNLIQNLISSTSST-2