Tied-LoRA: Enhancing parameter efficiency of LoRA with Weight Tying

Adithya Renduchintala, Tugrul Konuk, Oleksii Kuchaiev


Abstract
We introduce Tied-LoRA, a novel paradigm leveraging weight tying and selective training to enhance the parameter efficiency of Low-rank Adaptation (LoRA). Our exploration encompasses different plausible combinations of parameter training and freezing, coupled with weight tying, aimed at identifying the optimal trade-off between performance and the count of trainable parameters. Across 5 diverse tasks and two foundational language models with different parameter counts, our experiments provide comprehensive insights into the inherent trade-offs between efficiency and performance.Our findings reveal a specific Tied-LoRA configuration that distinguishes itself by showcasing comparable performance to LoRA across multiple tasks while utilizing only a fraction of the parameters employed by the standard LoRA method, particularly at elevated ranks. This underscores the efficacy of Tied-LoRA in achieving impressive results with significantly reduced model complexity.
Anthology ID:
2024.naacl-long.481
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8694–8705
Language:
URL:
https://aclanthology.org/2024.naacl-long.481
DOI:
10.18653/v1/2024.naacl-long.481
Bibkey:
Cite (ACL):
Adithya Renduchintala, Tugrul Konuk, and Oleksii Kuchaiev. 2024. Tied-LoRA: Enhancing parameter efficiency of LoRA with Weight Tying. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 8694–8705, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Tied-LoRA: Enhancing parameter efficiency of LoRA with Weight Tying (Renduchintala et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.481.pdf