Learning Graph Topological Features via GAN
This addresses the challenge of graph topological analysis for researchers in graph learning, though it appears incremental as it adapts GANs from images to graphs.
The paper tackles the problem of learning topological features from a single input graph by introducing a novel hierarchical GAN architecture that preserves local and global features and partitions the graph into stages for reconstruction, with experiments showing it retains a wide range of features even in early stages unlike single GANs.
Inspired by the generation power 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 (unlike a single GAN, which cannot easily identify such features, let alone reconstruct the original graph). This paper is firstline research on combining the use of GANs and graph topological analysis.