Multi-MotifGAN (MMGAN): Motif-targeted Graph Generation and Prediction

TL;DR

Multi-MotifGAN (MMGAN) is a novel GAN-based model that captures higher-order network motifs in graph generation, improving the realism of synthetic networks by focusing on motif structures like triangles.

Contribution

It introduces a motif-targeted GAN that combines multiple biased random walks to better replicate higher-order network motifs in generated graphs.

Findings

MMGAN outperforms NetGAN in capturing network motif statistics.

It accurately reproduces higher-order structures in real-world networks.

The approach improves the realism of generated graphs.

Abstract

Generative graph models create instances of graphs that mimic the properties of real-world networks. Generative models are successful at retaining pairwise associations in the underlying networks but often fail to capture higher-order connectivity patterns known as network motifs. Different types of graphs contain different network motifs, an example of which are triangles that often arise in social and biological networks. It is hence vital to capture these higher-order structures to simulate real-world networks accurately. We propose Multi-MotifGAN (MMGAN), a motif-targeted Generative Adversarial Network (GAN) that generalizes the benchmark NetGAN approach. The generalization consists of combining multiple biased random walks, each of which captures a different motif structure. MMGAN outperforms NetGAN at creating new graphs that accurately reflect the network motif statistics of input graphs such as Citeseer, Cora and Facebook.