Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning
It addresses data privacy and communication efficiency challenges for stakeholders in domains like finance and medical science collaborating on LLM fine-tuning, representing an incremental improvement by combining existing techniques.
The paper tackles the problem of fine-tuning large language models (LLMs) with sensitive data from multiple stakeholders by introducing DP-LoRA, a federated learning algorithm that ensures data privacy through a Gaussian mechanism and reduces communication overhead via low-rank adaptation, achieving strict privacy constraints and minimized overhead across medical, financial, and general datasets.
The surge in interest and application of large language models (LLMs) has sparked a drive to fine-tune these models to suit specific applications, such as finance and medical science. However, concerns regarding data privacy have emerged, especially when multiple stakeholders aim to collaboratively enhance LLMs using sensitive data. In this scenario, federated learning becomes a natural choice, allowing decentralized fine-tuning without exposing raw data to central servers. Motivated by this, we investigate how data privacy can be ensured in LLM fine-tuning through practical federated learning approaches, enabling secure contributions from multiple parties to enhance LLMs. Yet, challenges arise: 1) despite avoiding raw data exposure, there is a risk of inferring sensitive information from model outputs, and 2) federated learning for LLMs incurs notable communication overhead. To address these challenges, this article introduces DP-LoRA, a novel federated learning algorithm tailored for LLMs. DP-LoRA preserves data privacy by employing a Gaussian mechanism that adds noise in weight updates, maintaining individual data privacy while facilitating collaborative model training. Moreover, DP-LoRA optimizes communication efficiency via low-rank adaptation, minimizing the transmission of updated weights during distributed training. The experimental results across medical, financial, and general datasets using various LLMs demonstrate that DP-LoRA effectively ensures strict privacy constraints while minimizing communication overhead.