Can GAN Learn Topological Features of a Graph?

2017/07/19 by Weiyi Liu, Liu, Weiyi, Pin-Yu Chen +9
Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1707.06197

arxiv created 2017/07/19 · arxiv updated 2017/07/20

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.

Related

• Learning Graph Topological Features via GAN
• GraphGAN: Graph Representation Learning with Generative Adversarial Nets
• Enhancing Graph Representation Learning with Localized Topological Features
• GANTL: Towards Practical and Real-Time Topology Optimization with Conditional GANs and Transfer Learning
• Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology