NetGAN: Generating Graphs via Random Walks
This work addresses the challenge of graph generation for network analysis, offering a novel approach that combines generative modeling with generalization properties, though it is incremental as it builds on existing GAN frameworks.
The authors tackled the problem of generating realistic graphs by learning the distribution of biased random walks over input graphs, resulting in a model that produces graphs exhibiting well-known network patterns and achieves competitive link prediction performance without specific training for that task.
We propose NetGAN - the first implicit generative model for graphs able to mimic real-world networks. We pose the problem of graph generation as learning the distribution of biased random walks over the input graph. The proposed model is based on a stochastic neural network that generates discrete output samples and is trained using the Wasserstein GAN objective. NetGAN is able to produce graphs that exhibit well-known network patterns without explicitly specifying them in the model definition. At the same time, our model exhibits strong generalization properties, as highlighted by its competitive link prediction performance, despite not being trained specifically for this task. Being the first approach to combine both of these desirable properties, NetGAN opens exciting avenues for further research.