GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models

Jiaxuan You, Rex Ying, Xiang Ren, William Hamilton, Jure Leskovec
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:5708-5717, 2018.

Abstract

Modeling and generating graphs is fundamental for studying networks in biology, engineering, and social sciences. However, modeling complex distributions over graphs and then efficiently sampling from these distributions is challenging due to the non-unique, high-dimensional nature of graphs and the complex, non-local dependencies that exist between edges in a given graph. Here we propose GraphRNN, a deep autoregressive model that addresses the above challenges and approximates any distribution of graphs with minimal assumptions about their structure. GraphRNN learns to generate graphs by training on a representative set of graphs and decomposes the graph generation process into a sequence of node and edge formations, conditioned on the graph structure generated so far. In order to quantitatively evaluate the performance of GraphRNN, we introduce a benchmark suite of datasets, baselines and novel evaluation metrics based on Maximum Mean Discrepancy, which measure distances between sets of graphs. Our experiments show that GraphRNN significantly outperforms all baselines, learning to generate diverse graphs that match the structural characteristics of a target set, while also scaling to graphs 50 times larger than previous deep models.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-you18a, title = {{G}raph{RNN}: Generating Realistic Graphs with Deep Auto-regressive Models}, author = {You, Jiaxuan and Ying, Rex and Ren, Xiang and Hamilton, William and Leskovec, Jure}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {5708--5717}, 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/you18a/you18a.pdf}, url = {https://proceedings.mlr.press/v80/you18a.html}, abstract = {Modeling and generating graphs is fundamental for studying networks in biology, engineering, and social sciences. However, modeling complex distributions over graphs and then efficiently sampling from these distributions is challenging due to the non-unique, high-dimensional nature of graphs and the complex, non-local dependencies that exist between edges in a given graph. Here we propose GraphRNN, a deep autoregressive model that addresses the above challenges and approximates any distribution of graphs with minimal assumptions about their structure. GraphRNN learns to generate graphs by training on a representative set of graphs and decomposes the graph generation process into a sequence of node and edge formations, conditioned on the graph structure generated so far. In order to quantitatively evaluate the performance of GraphRNN, we introduce a benchmark suite of datasets, baselines and novel evaluation metrics based on Maximum Mean Discrepancy, which measure distances between sets of graphs. Our experiments show that GraphRNN significantly outperforms all baselines, learning to generate diverse graphs that match the structural characteristics of a target set, while also scaling to graphs 50 times larger than previous deep models.} }
Endnote
%0 Conference Paper %T GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models %A Jiaxuan You %A Rex Ying %A Xiang Ren %A William Hamilton %A Jure Leskovec %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-you18a %I PMLR %P 5708--5717 %U https://proceedings.mlr.press/v80/you18a.html %V 80 %X Modeling and generating graphs is fundamental for studying networks in biology, engineering, and social sciences. However, modeling complex distributions over graphs and then efficiently sampling from these distributions is challenging due to the non-unique, high-dimensional nature of graphs and the complex, non-local dependencies that exist between edges in a given graph. Here we propose GraphRNN, a deep autoregressive model that addresses the above challenges and approximates any distribution of graphs with minimal assumptions about their structure. GraphRNN learns to generate graphs by training on a representative set of graphs and decomposes the graph generation process into a sequence of node and edge formations, conditioned on the graph structure generated so far. In order to quantitatively evaluate the performance of GraphRNN, we introduce a benchmark suite of datasets, baselines and novel evaluation metrics based on Maximum Mean Discrepancy, which measure distances between sets of graphs. Our experiments show that GraphRNN significantly outperforms all baselines, learning to generate diverse graphs that match the structural characteristics of a target set, while also scaling to graphs 50 times larger than previous deep models.
APA
You, J., Ying, R., Ren, X., Hamilton, W. & Leskovec, J.. (2018). GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:5708-5717 Available from https://proceedings.mlr.press/v80/you18a.html.

Related Material