A generative neural network model for random dot product graphs
This work addresses the challenge of generating realistic random graphs for applications in various domains, but it appears incremental as it builds on existing neural network and graphlet-based methods.
The authors tackled the problem of learning generative models for random graphs by introducing GraphMoE, a neural network that matches graph distributions using moment estimators and graphlet features, producing graphs that can imitate data from chemistry, medicine, and social networks and fool discriminator networks.
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.