提出高效联邦离散提示学习框架，显著降低云端大模型调用次数。
FedOne: Query-Efficient Federated Learning for Black-box Discrete Prompt Learning
- 每轮仅激活一个客户端，极大减少云端调用次数。
- 实验显示查询效率提升明显，理论与实际一致。
- 适合资源受限下多源数据协同优化提示词的场景。
黑盒离散提示学习是一种无需访问模型参数或梯度即可优化离散提示的方法，使在基于云的大语言模型（LLM）上进行提示调优成为可能。将联邦学习应用于黑盒离散提示学习可借助多样化数据源提升调优性能。然而，以往研究均忽视了云服务带来的高昂查询成本。为此，我们对联邦黑盒提示学习中的查询效率进行了理论分析，发现将FedAvg退化为每轮仅激活一个客户端（即提出的FedOne策略）可实现最优查询效率。基于此，我们构建了FedOne框架，一种专为最大化与云端LLM交互时查询效率而设计的联邦黑盒离散提示学习方法。我们在多个方面开展数值实验，结果表明查询效率显著提升，与理论分析一致。
原文摘要 · Abstract (English)
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 \textit{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.
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。