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.
Описание
[1802.08773] GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
%0 Generic
%1 you2018graphrnn
%A You, Jiaxuan
%A Ying, Rex
%A Ren, Xiang
%A Hamilton, William L.
%A Leskovec, Jure
%D 2018
%K 2018 arxiv deep-learning graph icml paper stanford
%T GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
%U http://arxiv.org/abs/1802.08773
%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.
@misc{you2018graphrnn,
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.},
added-at = {2018-07-11T19:18:21.000+0200},
author = {You, Jiaxuan and Ying, Rex and Ren, Xiang and Hamilton, William L. and Leskovec, Jure},
biburl = {https://www.bibsonomy.org/bibtex/2526f6b87f5e96347d9874bbbaf093c77/analyst},
description = {[1802.08773] GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models},
interhash = {fba8e57849062ef3f0b9ff304424f06a},
intrahash = {526f6b87f5e96347d9874bbbaf093c77},
keywords = {2018 arxiv deep-learning graph icml paper stanford},
note = {cite arxiv:1802.08773Comment: ICML 2018},
timestamp = {2018-07-11T19:18:21.000+0200},
title = {GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models},
url = {http://arxiv.org/abs/1802.08773},
year = 2018
}