MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning

Pengjie Ren, Chengshun Shi, Shiguang Wu, Mengqi Zhang, Zhaochun Ren, Maarten de Rijke, Zhumin Chen, Jiahuan Pei


Abstract
Parameter-efficient fine-tuning (PEFT) is a popular method for tailoring pre-trained large language models (LLMs), especially as the models’ scale and the diversity of tasks increase. Low-rank adaptation (LoRA) is based on the idea that the adaptation process is intrinsically low-dimensional, i.e., significant model changes can be represented with relatively few parameters. However, decreasing the rank encounters challenges with generalization errors for specific tasks when compared to full-parameter fine-tuning. We present MELoRA, a mini-ensemble low-rank adapters that uses fewer trainable parameters while maintaining a higher rank, thereby offering improved performance potential.The core idea is to freeze original pretrained weights and train a group of mini LoRAs with only a small number of parameters. This can capture a significant degree of diversity among mini LoRAs, thus promoting better generalization ability. We conduct a theoretical analysis and empirical studies on various NLP tasks. Our experimental results show that, compared to LoRA, MELoRA achieves better performance with 8 times fewer trainable parameters on natural language understanding tasks and 36 times fewer trainable parameters on instruction following tasks, which demonstrates the effectiveness of MELoRA.
Anthology ID:
2024.acl-long.168
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:
3052–3064
Language:
URL:
https://aclanthology.org/2024.acl-long.168
DOI:
10.18653/v1/2024.acl-long.168
Bibkey:
Cite (ACL):
Pengjie Ren, Chengshun Shi, Shiguang Wu, Mengqi Zhang, Zhaochun Ren, Maarten de Rijke, Zhumin Chen, and Jiahuan Pei. 2024. MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3052–3064, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning (Ren et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.168.pdf