This is the work flow of Graph Topology Interpolater (GTI), with focus on the GAN, Sum-up and Stage Identification modules. At a high level, GTI methods takes an input gr...
Abstract:
Inspired by the generation power of generative adversarial networks (GANs) in image domains, we introduce a novel hierarchical architecture for learning characteristic to...Show MoreMetadata
Abstract:
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. The 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 the firstline research on combining the use of GANs and graph topological analysis.
This is the work flow of Graph Topology Interpolater (GTI), with focus on the GAN, Sum-up and Stage Identification modules. At a high level, GTI methods takes an input gr...
Published in: IEEE Access ( Volume: 7)