Graph Topological Features via GAN

Weiyi Liu, Hal Cooper, Min-Hwan Oh

Abstract: Inspired by the success of generative adversarial networks (GANs) in image domains, we introduce a novel hierarchical architecture for learning characteristic topological features from a single arbitrary input graph via GANs. The hierarchical architecture consisting of multiple GANs preserves both local and global topological features, and automatically partitions the input graph into representative stages for feature learning. The stages facilitate reconstruction and can be used as indicators of the importance of the associated topological structures. Experiments show that our method produces subgraphs retaining a wide range of topological features, even in early reconstruction stages. This paper contains original research on combining the use of GANs and graph topological analysis.

TL;DR: A GAN based method to learn important topological features of an arbitrary input graph.

Keywords: graph topology, GAN, network science, hierarchical learning