arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.01752cs.LGcs.DC
收藏

垂直联合主成分分析及其核扩展

Vertical Federated Principal Component Analysis and Its Kernel Extension on Feature-wise Distributed Data

Hong Kong Baptist University(香港浸会大学);Xidian University(西安电子科技大学)

Yiu-ming Cheung, Juyong Jiang, Feng Yu, Jian Lou

摘要:

尽管联邦学习(FL)在各个领域有着巨大的研究兴趣和快速的应用,但现有的研究大多集中在水平分区局部数据集环境下的有监督联邦学习。本文将研究垂直分区数据集下的无监督FL。因此,本文提出了垂直分区数据集联合主成分分析(VFedPCA)方法,该方法对所有客户端的联合数据集进行降维,并提取主成分特征信息用于下游数据分析。我们进一步利用非线性降维,并提出了垂直联邦高级核主成分分析(VFedAKPCA)方法,它可以有效地和协同建模的非线性性质存在于许多真实的数据集。此外,我们还研究了两种通信拓扑结构。第一种是服务器-客户端拓扑,其中半信任服务器协调联合训练,而第二种是完全分散的拓扑,通过允许客户端自己与邻居通信,进一步消除了对服务器的要求。在五种真实数据集上进行的大量实验证实了垂直分区FL设置下VFedPCA和VFedAKPCA的有效性。代码可在:https://github.com/juyongjiang/VFedPCA-VFedAKPCA

英文摘要:

Despite enormous research interest and rapid application of federated learning (FL) to various areas, existing studies mostly focus on supervised federated learning under the horizontally partitioned local dataset setting. This paper will study the unsupervised FL under the vertically partitioned dataset setting. Accordingly, we propose the federated principal component analysis for vertically partitioned dataset (VFedPCA) method, which reduces the dimensionality across the joint datasets over all the clients and extracts the principal component feature information for downstream data analysis. We further take advantage of the nonlinear dimensionality reduction and propose the vertical federated advanced kernel principal component analysis (VFedAKPCA) method, which can effectively and collaboratively model the nonlinear nature existing in many real datasets. In addition, we study two communication topologies. The first is a server-client topology where a semi-trusted server coordinates the federated training, while the second is the fully-decentralized topology which further eliminates the requirement of the server by allowing clients themselves to communicate with their neighbors. Extensive experiments conducted on five types of real-world datasets corroborate the efficacy of VFedPCA and VFedAKPCA under the vertically partitioned FL setting. Code is available at: https://github.com/juyongjiang/VFedPCA-VFedAKPCA

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。

↑