Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning

Tuc Nguyen, Thai Le

Abstract
Several parameter-efficient fine-tuning methods based on adapters have been proposed as a streamlined approach to incorporate not only a single specialized knowledge into existing Pre-Trained Language Models (PLMs) but also multiple of them at once. Recent works such as AdapterSoup propose to mix not all but only a selective sub-set of domain-specific adapters during inference via model weight averaging to optimize performance on novel, unseen domains with excellent computational efficiency. However, the essential generalizability of this emerging weight-space adapter mixing mechanism on unseen, in-domain examples remains unexplored. Thus, in this study, we conduct a comprehensive analysis to elucidate the generalizability of domain-specific adapter mixtures in in-domain evaluation. We also provide investigations into the inner workings of the mixture of domain-specific adapters by analyzing their weight signs, yielding critical analysis on the negative correlation between their fraction of weight sign difference and their mixtures’ generalizability. The code is available at Github.
Anthology ID:
2024.acl-long.700
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12956–12973
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.acl-long.700/
DOI:
10.18653/v1/2024.acl-long.700
Bibkey:
Cite (ACL):
Tuc Nguyen and Thai Le. 2024. Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12956–12973, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning (Nguyen & Le, ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.acl-long.700.pdf
PDF Search Fix metadata