FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt Learning

2025/06/17 by Wang, Ganyu, Fang, Jinjie, Yin, Maxwell J. +5 · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2506.14929

Abstract

Black-Box Discrete Prompt Learning is a prompt-tuning method that optimizes discrete prompts without accessing model parameters or gradients, making the prompt tuning on a cloud-based Large Language Model (LLM) feasible. Adapting federated learning to BDPL could further enhance prompt tuning performance by leveraging data from diverse sources. However, all previous research on federated black-box prompt tuning had neglected the substantial query cost associated with the cloud-based LLM service. To address this gap, we conducted a theoretical analysis of query efficiency within the context of federated black-box prompt tuning. Our findings revealed that degrading FedAvg to activate only one client per round, a strategy we called FedOne, enabled optimal query efficiency in federated black-box prompt learning. Building on this insight, we proposed the FedOne framework, a federated black-box discrete prompt learning method designed to maximize query efficiency when interacting with cloud-based LLMs. We conducted numerical experiments on various aspects of our framework, demonstrating a significant improvement in query efficiency, which aligns with our theoretical results.

Cited by

• FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits

Related

• FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models
• FedDTPT: Federated Discrete and Transferable Prompt Tuning for Black-Box Large Language Models
• FedDPG: An Adaptive Yet Efficient Prompt-tuning Approach in Federated Learning Settings
• FedPT: Federated Proxy-Tuning of Large Language Models on Resource-Constrained Edge Devices
• Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization