Fast Randomized Low-Rank Adaptation of Pre-trained Language Models with PAC Regularization

Zijian Lei, Dong Qian, William Cheung


Abstract
Low-rank adaptation (LoRA) achieves parameter efficient fine-tuning for large language models (LLMs) by decomposing the model weight update into a pair of low-rank projection matrices. Yet, the memory overhead restricts it to scale up when the model size increases. We propose Randomized LoRA (RLoRA) which adopts Randomized Walsh-Hadamard Transform to achieve significant reduction in the size of trainable parameters compared to LoRA. At the same time, it allows a PAC-Bayes regularizer to be efficiently incorporated to improve generalization. We evaluate the effectiveness of RLoRA on LLMs RoBERTa, GPT-2 and LLaMA-7B using GLUE, E2E and math reasoning benchmarks. With a much lower memory requirement, RLoRA can give similar performance as the SOTA low-rank adaptation methods for these three tasks and significantly better performance under few-shot settings.
Anthology ID:
2024.findings-acl.310
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5236–5249
Language:
URL:
https://aclanthology.org/2024.findings-acl.310
DOI:
Bibkey:
Cite (ACL):
Zijian Lei, Dong Qian, and William Cheung. 2024. Fast Randomized Low-Rank Adaptation of Pre-trained Language Models with PAC Regularization. In Findings of the Association for Computational Linguistics ACL 2024, pages 5236–5249, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Fast Randomized Low-Rank Adaptation of Pre-trained Language Models with PAC Regularization (Lei et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.310.pdf