This paper presents GraphFederator, a novel approach to construct joint 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 joint 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 views for joint visualization, exploration, and analysis of multi-party graphs. Experimental results with two datasets demonstrate the effectiveness of our approach.
@article{arxiv.2008.11989,
title = {GraphFederator: Federated Visual Analysis for Multi-party Graphs},
author = {Dongming Han and Wei Chen and Rusheng Pan and Yijing Liu and Jiehui Zhou and Ying Xu and Tianye Zhang and Changjie Fan and Jianrong Tao and Xiaolong and Zhang},
journal= {arXiv preprint arXiv:2008.11989},
year = {2020}
}