Timezone: »

NetGAN: Generating Graphs via Random Walks
Aleksandar Bojchevski · Oleksandr Shchur · Daniel Zügner · Stephan Günnemann

Wed Jul 11 08:20 AM -- 08:40 AM (PDT) @ A5

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.

Author Information

Aleksandar Bojchevski (Technical University of Munich)
Oleksandr Shchur (Technical University of Munich)
Daniel Zügner (Technical University of Munich)

PhD candidate @ **TU Munich**. Research on robust machine learning for graphs. Previous: R&D intern @ **Apple**, machine learning for music data.

Stephan Günnemann (Technical University of Munich)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors