用合成数据实现大模型联邦学习，保护隐私还省资源
LanFL: Differentially Private Federated Learning with Large Language Models using Synthetic Samples
- 纯提示驱动，把大模型当黑箱不用微调
- 差分隐私生成合成数据，本地数据不外泄
- 适合无模型权重的用户参与，隐私敏感场景适用
联邦学习（FL）是一种协作式、隐私保护的机器学习框架，允许多方协同训练一个全局模型。然而，参数达数十亿至数百亿的大语言模型（LLMs）使传统FL方法难以直接应用，因计算与通信开销过高。此外，大多数用户无法获取大模型的完整架构和权重，无法直接进行微调。本文提出一种新型大模型联邦学习方案LanFL，完全基于提示（prompt），将底层大模型视为黑箱。我们设计了一种差分隐私的合成样本生成机制，用于参与者间知识共享，并提出提示优化策略，使模型能从合成数据中学习。大量实验表明，LanFL在多种任务中成功实现多方协作学习，同时在不同场景下有效保护了本地数据隐私。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。