Vertical Federated Principal Component Analysis on Feature-wise Distributed Data

Yiu-ming Cheung*, Jian Lou, Feng Yu

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

Abstract

Despite the wide attention to federated learning (FL) in the literature, the 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 vertically dataset partitioned federated principal component analysis (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. VFedPCA features efficient local computation, communication efficiency, and privacy-preserving. Further, 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 eliminates the requirement of the server by allowing clients to communicate with their neighbors. Extensive experiments conducted on real-world datasets justify the efficacy of VFedPCA under vertical partitioned FL setting.
Original languageEnglish
Title of host publicationWeb Information Systems Engineering – WISE 2021
Subtitle of host publication22nd International Conference on Web Information Systems Engineering, WISE 2021, Melbourne, VIC, Australia, October 26–29, 2021, Proceedings, Part I
EditorsWenjie Zhang, Lei Zou, Zakaria Maamar, Lu Chen
PublisherSpringer Cham
Pages173-188
Number of pages16
Edition1st
ISBN (Electronic)9783030908881
ISBN (Print)9783030908874
DOIs
Publication statusPublished - 26 Oct 2021
Event22nd International Conference on Web Information Systems Engineering, WISE 2021 - Melbourne, Australia
Duration: 26 Oct 202129 Oct 2021

Publication series

NameLecture Notes in Computer Science
Volume13080
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameInformation Systems and Applications, incl. Internet/Web, and HCI
Volume13080
NameWISE: International Conference on Web Information Systems Engineering

Conference

Conference22nd International Conference on Web Information Systems Engineering, WISE 2021
Country/TerritoryAustralia
CityMelbourne
Period26/10/2129/10/21

User-Defined Keywords

  • Principal component analysis
  • Federated learning
  • Vertical distributed data

Fingerprint

Dive into the research topics of 'Vertical Federated Principal Component Analysis on Feature-wise Distributed Data'. Together they form a unique fingerprint.

Cite this