Multi-MotifGAN (MMGAN): Motif-targeted Graph Generation and Prediction
This work addresses the challenge of simulating real-world networks more accurately for domains like social and biological networks, though it is incremental as it generalizes an existing benchmark.
The authors tackled the problem of generative graph models failing to capture higher-order connectivity patterns like network motifs, proposing Multi-MotifGAN (MMGAN) which outperforms NetGAN in generating graphs that accurately reflect motif statistics on datasets such as Citeseer, Cora, and Facebook.
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.