A generative neural network model for random dot product graphs

TL;DR

This paper introduces GraphMoE, a neural network model that learns to generate random graphs by matching subgraph distributions, effectively mimicking real-world network data across various domains.

Contribution

It presents a novel neural network approach using graphlet-based features to generate realistic random graphs that can imitate complex data from multiple fields.

Findings

Generated graphs can fool discriminator neural networks.

The model successfully mimics data from chemistry, medicine, and social networks.

Graphs produced are similar to real data in structure and distribution.

Abstract

We present GraphMoE, a novel neural network-based approach to learning generative models for random graphs. The neural network is trained to match the distribution of a class of random graphs by way of a moment estimator. The features used for training are graphlets, subgraph counts of small order. The neural network accepts random noise as input and outputs vector representations for nodes in the graph. Random graphs are then realized by applying a kernel to the representations. Graphs produced this way are demonstrated to be able to imitate data from chemistry, medicine, and social networks. The produced graphs are similar enough to the target data to be able to fool discriminator neural networks otherwise capable of separating classes of random graphs.