DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model

Chao Gao, Sai Qian Zhang


Abstract
To enhance the performance of large language models (LLM) on downstream tasks, one solution is to fine-tune certain LLM parameters and make them better align with the characteristics of the training dataset. This process is commonly known as parameter-efficient fine-tuning (PEFT). Due to the scale of LLM, PEFT operations are usually executed in the public environment (e.g., cloud server). This necessitates sharing sensitive user data across public environments, thereby raising potential privacy concerns. To tackle these challenges, we propose a distributed PEFT framework called DLoRA. DLoRA enables scalable PEFT operations to be performed collaboratively between the cloud and user devices. Coupled with the proposed Kill and Revive algorithm, the evaluation results demonstrate that DLoRA can significantly reduce the computation and communication workload over user devices while achieving superior accuracy and privacy protection.
Anthology ID:
2024.findings-emnlp.802
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13703–13714
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.802
DOI:
Bibkey:
Cite (ACL):
Chao Gao and Sai Qian Zhang. 2024. DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 13703–13714, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model (Gao & Zhang, Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.802.pdf