HetVis: A Visual Analysis Approach for Identifying Data Heterogeneity in Horizontal Federated Learning

Xumeng Wang, Wei Chen, Jiazhi Xia, Zhen Wen, Rongchen Zhu, Tobias Schreck

Research output: Contribution to journalArticle

Abstract

Horizontal federated learning (HFL) enables distributed clients to train a shared model and keep their data privacy. In training high-quality HFL models, the data heterogeneity among clients is one of the major concerns. However, due to the security issue and the complexity of deep learning models, it is challenging to investigate data heterogeneity across different clients. To address this issue, based on a requirement analysis we developed a visual analytics tool, HetVis, for participating clients to explore data heterogeneity. We identify data heterogeneity through comparing prediction behaviors of the global federated model and the stand-alone model trained with local data. Then, a context-aware clustering of the inconsistent records is done, to provide a summary of data heterogeneity. Combining with the proposed comparison techniques, we develop a novel set of visualizations to identify heterogeneity issues in HFL. We designed three case studies to introduce how HetVis can assist client analysts in understanding different types of heterogeneity issues. Expert reviews and a comparative study demonstrate the effectiveness of HetVis.
Original languageEnglish
Pages (from-to)310-319
Number of pages10
JournalIEEE Transactions on Visualization and Computer Graphics
Volume29
Issue number1
DOIs
Publication statusPublished - 1 Jan 2023

Keywords

  • cluster analysis
  • data heterogeneity
  • Federated learning
  • visual analysis

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Fields of Expertise

  • Information, Communication & Computing

Fingerprint

Dive into the research topics of 'HetVis: A Visual Analysis Approach for Identifying Data Heterogeneity in Horizontal Federated Learning'. Together they form a unique fingerprint.

Cite this