FedPerfix：面向联邦学习中 Vision Transformer 的部分模型个性化
FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning
AI总结：
针对 ViT 在个性化联邦学习中的部分个性化问题，本文依据各层数据分布敏感性提出 FedPerfix，用插件向本地客户端传递聚合模型信息，并在三个数据集上验证其优于先进 PFL 方法。
摘要：
个性化联邦学习（PFL）是异构数据环境中去中心化学习的一种有前景的解决方案。部分模型个性化已被提出，通过选择性地更新本地模型参数而非聚合全部参数来提升 PFL 的效率。然而，以往关于部分模型个性化的工作主要集中于卷积神经网络（CNN），在如何将其应用于 Vision Transformer（ViT）等其他流行模型方面仍存在空白。在本工作中，我们研究在何处以及如何对 ViT 模型进行部分个性化。具体而言，我们通过实验评估了每一类层对数据分布的敏感性。基于自注意力层和分类头是 ViT 中最敏感部分的洞见，我们提出了一种名为 FedPerfix 的新方法，该方法利用插件将聚合模型中的信息传递给本地客户端，以此实现个性化。最后，我们在 CIFAR-100、OrganAMNIST 和 Office-Home 数据集上评估了所提出的方法，并证明与若干先进 PFL 方法相比，该方法在提升模型性能方面的有效性。
英文摘要：
Personalized Federated Learning (PFL) represents a promising solution for decentralized learning in heterogeneous data environments. Partial model personalization has been proposed to improve the efficiency of PFL by selectively updating local model parameters instead of aggregating all of them. However, previous work on partial model personalization has mainly focused on Convolutional Neural Networks (CNNs), leaving a gap in understanding how it can be applied to other popular models such as Vision Transformers (ViTs). In this work, we investigate where and how to partially personalize a ViT model. Specifically, we empirically evaluate the sensitivity to data distribution of each type of layer. Based on the insights that the self-attention layer and the classification head are the most sensitive parts of a ViT, we propose a novel approach called FedPerfix, which leverages plugins to transfer information from the aggregated model to the local client as a personalization. Finally, we evaluate the proposed approach on CIFAR-100, OrganAMNIST, and Office-Home datasets and demonstrate its effectiveness in improving the model's performance compared to several advanced PFL methods.
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。
