@inproceedings{gao-zhang-2024-dlora,
title = "{DL}o{RA}: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model",
author = "Gao, Chao and
Zhang, Sai Qian",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.802",
pages = "13703--13714",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-zhang-2024-dlora">
<titleInfo>
<title>DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Qian</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">gao-zhang-2024-dlora</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.802</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>13703</start>
<end>13714</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model
%A Gao, Chao
%A Zhang, Sai Qian
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F gao-zhang-2024-dlora
%X 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.
%U https://aclanthology.org/2024.findings-emnlp.802
%P 13703-13714
Markdown (Informal)
[DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model](https://aclanthology.org/2024.findings-emnlp.802) (Gao & Zhang, Findings 2024)
ACL