GraphFederator: Federated Visual Analysis for Multi-party Graphs

This paper presents GraphFederator, a novel approach to construct federated representations of multi-party graphs and supports privacy-preserving visual analysis of graphs. Inspired by the concept of federated learning, we reformulate the analysis of multi-party graphs into a decentralization proces...

Full description

Saved in:
Bibliographic Details
Main Authors: Han, Dongming, Zhu, Haiyang, Chen, Wei, Pan, Rusheng, Liu, Yijing, Zhou, Jiehui, Feng, Haozhe, Zhang, Tianye, Wang, Xumeng, Zhu, Minfeng, Tao, Jianrong, Fan, Changjie, Zhang, Xiaolong Luke
Format: Conference Proceeding
Language:English
Subjects:
Analytical models
Data models
Data visualization
Encryption
Federated learning
Graph analysis
Graph visual analysis
Representation learning
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents GraphFederator, a novel approach to construct federated representations of multi-party graphs and supports privacy-preserving visual analysis of graphs. Inspired by the concept of federated learning, we reformulate the analysis of multi-party graphs into a decentralization process. The new federation framework consists of a shared module that is responsible for federated modeling and analysis, and a set of local modules that run on respective graph data. Specifically, we propose a Federated Graph Representation Model (FGRM) that is learned from encrypted characteristics of multi-party graphs in local modules. We also design multiple visualization tools for federated visualization, exploration, and analysis of multi-party graphs. Experimental results on two datasets demonstrate the effectiveness of our approach.
ISSN:2165-8773
DOI:10.1109/PacificVis60374.2024.00027