NetGAN: Generating Graphs via Random Walks

Aleksandar Bojchevski, Oleksandr Shchur, Daniel Zügner, Stephan Günnemann
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:610-619, 2018.

Abstract

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-bojchevski18a, title = {{N}et{GAN}: Generating Graphs via Random Walks}, author = {Bojchevski, Aleksandar and Shchur, Oleksandr and Z{\"u}gner, Daniel and G{\"u}nnemann, Stephan}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {610--619}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/bojchevski18a/bojchevski18a.pdf}, url = {https://proceedings.mlr.press/v80/bojchevski18a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T NetGAN: Generating Graphs via Random Walks %A Aleksandar Bojchevski %A Oleksandr Shchur %A Daniel Zügner %A Stephan Günnemann %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-bojchevski18a %I PMLR %P 610--619 %U https://proceedings.mlr.press/v80/bojchevski18a.html %V 80 %X 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.
APA
Bojchevski, A., Shchur, O., Zügner, D. & Günnemann, S.. (2018). NetGAN: Generating Graphs via Random Walks. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:610-619 Available from https://proceedings.mlr.press/v80/bojchevski18a.html.

Related Material