Can GAN Learn Topological Features of a Graph?

TL;DR

This research demonstrates that GANs can effectively learn and preserve the topological features of arbitrary graphs by leveraging their hierarchical connectivity, enabling ranking of edges and maintaining key topological properties.

Contribution

It introduces a novel application of GANs for graph topology analysis, showing their ability to capture and preserve complex topological features.

Findings

GANs successfully capture graph topological features

Edge ranking correlates with topology contribution

Stages preserve important topological properties

Abstract

This paper is first-line research expanding GANs into graph topology analysis. By leveraging the hierarchical connectivity structure of a graph, we have demonstrated that generative adversarial networks (GANs) can successfully capture topological features of any arbitrary graph, and rank edge sets by different stages according to their contribution to topology reconstruction. Moreover, in addition to acting as an indicator of graph reconstruction, we find that these stages can also preserve important topological features in a graph.