论文信息 - STGGAN: Spatial-temporal Graph Generation

STGGAN: Spatial-temporal Graph Generation

This work addresses research on spatial-temporal graph generation and introduces a new model called "Spatial-temporal Graph Generative Adversarial Network" (STGGAN), which uses a newly developed variable-length Long Short Term Memory network via spatial-temporal random walks.

Liming Zhang

[1] Nikos Komodakis,et al. GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders , 2018, ICANN.

[2] Petter Holme,et al. Modern temporal network theory: a colloquium , 2015, The European Physical Journal B.

[3] Stephan Günnemann,et al. NetGAN: Generating Graphs via Random Walks , 2018, ICML.

[4] Amos J. Storkey,et al. Data Augmentation Generative Adversarial Networks , 2017, ICLR 2018.

[5] Jure Leskovec,et al. GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models , 2018, ICML.

[6] Edoardo M. Airoldi,et al. A Survey of Statistical Network Models , 2009, Found. Trends Mach. Learn..

[7] Yizhou Sun,et al. Personalized entity recommendation: a heterogeneous information network approach , 2014, WSDM.

[8] Stephan Günnemann,et al. Bayesian Robust Attributed Graph Clustering: Joint Learning of Partial Anomalies and Group Structure , 2018, AAAI.

[9] Carl A. Gunter,et al. Plausible Deniability for Privacy-Preserving Data Synthesis , 2017, Proc. VLDB Endow..