GraphFederator: Federated Visual Analysis for Multi-party Graphs

TL;DR

GraphFederator introduces a federated learning-inspired framework for privacy-preserving joint analysis and visualization of multi-party graphs, enabling decentralized graph modeling without sharing raw data.

Contribution

It proposes a novel federated graph representation model and visualization framework for multi-party graphs, enhancing privacy and collaborative analysis capabilities.

Findings

Effective joint graph representations learned from encrypted data

Supports privacy-preserving visualization and analysis

Validated on two datasets with positive results

Abstract

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.