联邦学习中的高效模型个性化：基于客户端特定提示生成
Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation
AI总结：
提出pFedPG框架，通过服务器端生成客户端特定视觉提示，实现联邦学习中高效且个性化的模型适配，优于现有方法。
摘要：
联邦学习（FL）作为一种去中心化的学习框架应运而生，它从多个分布式客户端训练模型，而无需共享其数据以保护隐私。近期，大规模预训练模型（如Vision Transformer）已展现出提取稳健表征的强大能力。然而，客户端之间的数据异质性、有限的计算资源以及通信带宽限制了大规模模型在FL框架中的部署。为了利用大规模模型的稳健表征，同时实现对异构客户端的高效模型个性化，我们提出了一种新颖的个性化FL框架——客户端特定提示生成（pFedPG），该框架学习在服务器端部署一个个性化提示生成器，以产生客户端特定的视觉提示，从而高效地将冻结的骨干网络适应于本地数据分布。我们提出的框架联合优化了本地个性化提示适应和全局个性化提示生成两个阶段。前者旨在训练视觉提示，使基础模型适应每个客户端；后者则观察本地优化方向，为所有客户端生成个性化提示。通过在基准数据集上的大量实验，我们表明，在各种类型的数据异质性下，我们的pFedPG优于最先进的个性化FL方法，实现了计算和通信高效的模型个性化。
英文摘要：
Federated learning (FL) emerges as a decentralized learning framework which trains models from multiple distributed clients without sharing their data to preserve privacy. Recently, large-scale pre-trained models (e.g., Vision Transformer) have shown a strong capability of deriving robust representations. However, the data heterogeneity among clients, the limited computation resources, and the communication bandwidth restrict the deployment of large-scale models in FL frameworks. To leverage robust representations from large-scale models while enabling efficient model personalization for heterogeneous clients, we propose a novel personalized FL framework of client-specific Prompt Generation (pFedPG), which learns to deploy a personalized prompt generator at the server for producing client-specific visual prompts that efficiently adapts frozen backbones to local data distributions. Our proposed framework jointly optimizes the stages of personalized prompt adaptation locally and personalized prompt generation globally. The former aims to train visual prompts that adapt foundation models to each client, while the latter observes local optimization directions to generate personalized prompts for all clients. Through extensive experiments on benchmark datasets, we show that our pFedPG is favorable against state-of-the-art personalized FL methods under various types of data heterogeneity, allowing computation and communication efficient model personalization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
