LanFL: Differentially Private Federated Learning with Large Language Models using Synthetic Samples
This addresses the problem of high computational costs and lack of model access in federated learning for LLMs, offering a practical solution for privacy-preserving collaborative training.
The paper tackles the challenge of applying federated learning to large language models by introducing LanFL, a prompt-based scheme that uses differentially private synthetic samples, and shows it enables learning while preserving privacy across tasks.
Federated Learning (FL) is a collaborative, privacy-preserving machine learning framework that enables multiple participants to train a single global model. However, the recent advent of powerful Large Language Models (LLMs) with tens to hundreds of billions of parameters makes the naive application of traditional FL methods to LLMs impractical due to high computational and communication costs. Furthermore, end users of LLMs often lack access to full architectures and weights of the models, making it impossible for participants to fine-tune these models directly. This paper introduces a novel FL scheme for LLMs, named LanFL, which is purely prompt-based and treats the underlying LLMs as black boxes. We have developed a differentially private synthetic sample generation mechanism to facilitate knowledge sharing among participants, along with a prompt optimization scheme that enables learning from synthetic samples. Our extensive experiments demonstrate that LanFL successfully facilitates learning among participants while preserving the privacy of local datasets across various tasks.