TY - JOUR
T1 - Misc-GAN
T2 - A Multi-scale Generative Model for Graphs
AU - Zhou, Dawei
AU - Zheng, Lecheng
AU - Xu, Jiejun
AU - He, Jingrui
N1 - Funding Information:
This material is supported by the National Science Foundation under Grant No. IIS-1651203, IIS-1715385, IIS-1743040, and CNS-1629888, by DTRA under the grant number HDTRA1-16-0017, by the United States Air Force and DARPA under contract number FA8750-17-C-01531, by Army Research Office under the contract number W911NF-16-1-0168, and by the U.S. Department of Homeland Security under Grant Award Number 2017-ST-061-QA0001. The content of the information in this document does not necessarily reflect the position or the policy of the Government, and no official endorsement should be inferred. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.
Publisher Copyright:
Copyright © 2019 Zhou, Zheng, Xu and He.
PY - 2019/4/25
Y1 - 2019/4/25
N2 - Characterizing and modeling the distribution of a particular family of graphs are essential for the studying real-world networks in a broad spectrum of disciplines, ranging from market-basket analysis to biology, from social science to neuroscience. However, it is unclear how to model these complex graph organizations and learn generative models from an observed graph. The key challenges stem from the non-unique, high-dimensional nature of graphs, as well as graph community structures at different granularity levels. In this paper, we propose a multi-scale graph generative model named Misc-GAN, which models the underlying distribution of graph structures at different levels of granularity, and then “transfers” such hierarchical distribution from the graphs in the domain of interest, to a unique graph representation. The empirical results on seven real data sets demonstrate the effectiveness of the proposed framework.
AB - Characterizing and modeling the distribution of a particular family of graphs are essential for the studying real-world networks in a broad spectrum of disciplines, ranging from market-basket analysis to biology, from social science to neuroscience. However, it is unclear how to model these complex graph organizations and learn generative models from an observed graph. The key challenges stem from the non-unique, high-dimensional nature of graphs, as well as graph community structures at different granularity levels. In this paper, we propose a multi-scale graph generative model named Misc-GAN, which models the underlying distribution of graph structures at different levels of granularity, and then “transfers” such hierarchical distribution from the graphs in the domain of interest, to a unique graph representation. The empirical results on seven real data sets demonstrate the effectiveness of the proposed framework.
KW - cycle consistency
KW - generative adversarial network
KW - graph generation
KW - multi-scale analysis method (MSA)
KW - neural network
UR - http://www.scopus.com/inward/record.url?scp=85071157648&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85071157648&partnerID=8YFLogxK
U2 - 10.3389/fdata.2019.00003
DO - 10.3389/fdata.2019.00003
M3 - Article
AN - SCOPUS:85071157648
SN - 2624-909X
VL - 2
JO - Frontiers in Big Data
JF - Frontiers in Big Data
M1 - 3
ER -