发表机构
University of Florida; Washington State University（佛罗里达大学; 华盛顿州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对非独立同分布与不平衡数据场景，提出基于最优传输的去中心化联邦提示调优算法D-FROST，解决异构本地提示索引不对齐问题，通过理论分析与实验验证了其有效性。
AI 中文摘要
提示调优是一种参数高效的方法，通过冻结预训练基础模型（Foundation Models, FMs）的主干网络，仅更新少量可学习提示，从而实现对基础模型的适配。该特性使提示调优尤其适用于去中心化联邦学习（Decentralized Federated Learning, DFL），因为在去中心化联邦学习中交换完整模型更新的成本可能高得难以承受。然而，去中心化联邦学习中的提示调优引入了新的挑战：从异构本地数据中学习到的提示集可能在索引上不对齐，导致标准的去中心化平均方法不再适用；此外，该算法需在理论上保证能达成共识并向共享目标推进。本研究首次对去中心化联邦学习中的提示调优展开研究，我们将去中心化提示调优建模为基于Wasserstein的提示测度优化问题，该问题可捕捉提示的集值结构。随后，我们提出了D-FROST，一种基于最优传输（Optimal Transport, OT）的去中心化提示调优算法，该算法通过基于传输的匹配将邻居节点的提示合并为紧凑的代表性提示集。我们进一步通过界定客户端间的Wasserstein共识误差、建立网络级提示重心向平稳性邻域收敛的特性，对D-FROST进行了分析。在异构客户端数据下开展的实验，验证了D-FROST用于去中心化提示调优的有效性。
英文摘要
Prompt tuning provides a parameter-efficient way to adapt foundation models (FMs) by freezing the pretrained backbone and updating only a small set of learnable prompts. This property makes prompt tuning especially suitable for decentralized federated learning (DFL), where exchanging full-model updates can be prohibitively expensive. However, prompt tuning in DFL introduces new challenges. Prompt sets learned from heterogeneous local data may not be index-wise aligned, making standard decentralized averaging unsuitable. In addition, the algorithm should be theoretically guaranteed to achieve consensus and make progress toward the shared objective. In this work, we provide the first study of prompt tuning in DFL. We formulate decentralized prompt tuning as a Wasserstein-based optimization problem over prompt measures, which captures the set-valued structure of prompts. We then propose D-FROST, an optimal-transport-based (OT-based) decentralized prompt-tuning algorithm that merges neighborhood prompts into compact representative prompt sets through transportation-based matching. We further analyze D-FROST by bounding the Wasserstein consensus error across clients, and establishing convergence of the network-level prompt barycenter to a neighborhood of stationarity. Experiments under heterogeneous client data demonstrate the effectiveness of D-FROST for decentralized prompt tuning.
