Can GAN Learn Topological Features of a Graph?
This addresses the challenge of graph topology analysis for researchers in machine learning and graph theory, representing incremental progress by applying GANs to a new domain.
The paper tackles the problem of whether generative adversarial networks (GANs) can learn topological features of graphs, demonstrating that they can capture these features and rank edge sets by their contribution to topology reconstruction, with the stages preserving important topological features.
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.