English

LoRA-SP: Streamlined Partial Parameter Adaptation for Resource-Efficient Fine-Tuning of Large Language Models

Machine Learning 2024-03-15 v1 Computation and Language

Abstract

In addressing the computational and memory demands of fine-tuning Large Language Models(LLMs), we propose LoRA-SP(Streamlined Partial Parameter Adaptation), a novel approach utilizing randomized half-selective parameter freezing within the Low-Rank Adaptation(LoRA)framework. This method efficiently balances pre-trained knowledge retention and adaptability for task-specific optimizations. Through a randomized mechanism, LoRA-SP determines which parameters to update or freeze, significantly reducing computational and memory requirements without compromising model performance. We evaluated LoRA-SP across several benchmark NLP tasks, demonstrating its ability to achieve competitive performance with substantially lower resource consumption compared to traditional full-parameter fine-tuning and other parameter-efficient techniques. LoRA-SP innovative approach not only facilitates the deployment of advanced NLP models in resource-limited settings but also opens new research avenues into effective and efficient model adaptation strategies.

Keywords

Cite

@article{arxiv.2403.08822,
  title  = {LoRA-SP: Streamlined Partial Parameter Adaptation for Resource-Efficient Fine-Tuning of Large Language Models},
  author = {Yichao Wu and Yafei Xiang and Shuning Huo and Yulu Gong and Penghao Liang},
  journal= {arXiv preprint arXiv:2403.08822},
  year   = {2024}
}
R2 v1 2026-06-28T15:19:11.303Z