Federated Black-box Prompt Tuning System for Large Language Models on the Edge
Year: 2024
Type: conference-paper
Abstract: Federated learning (FL) offers a privacy-preserving way to train models across decentralized data. However, fine-tuning pre-trained language models (PLMs) in FL is challenging due to restricted model parameter access, high computational demands, and communication overheads. Our method treats large language models (LLMs) as black-box inference APIs, optimizing prompts with gradient-free methods. This approach, FedBPT, reduces exchanged variables, boosts communication efficiency, and minimizes computational and memory costs. We demonstrate the practical implementation of FedBPT on resource-limited edge devices, showcasing its ability to efficiently achieve collaborative on-device LLM fine-tuning.
Authors: Yiming Li, Jingwei Sun, Yudong Liu, Yuandong Zhang, Ang Li, Beidi Chen, Holger R. Roth, Daguang Xu, Tingjun Chen, Yiran Chen
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4405014281