CSIS logoCenter for Secure Information Systems

Securing the World's Cyber Infrastructure

Aerial View of the George Mason Fairfax Campus

CSIS Seminar

Adversarial learning on deep graph generative models and applications

Speaker:   Liang Zhao, George Mason University
When:   March 1, 2019, 2:00 pm - 3:00 pm
Where:   Research Hall, Suite 417


Inspired by the tremendous success of deep generative models on generating continuous data like image and audio, in the most recent year, deep graph generative learning is becoming a promising domain which focuses on generating discrete data such as graphs. They are typically unconditioned generative models which has no control on modes of the graphs being generated. Going beyond that, in this presentation, we will talk about a new problem named Deep Graph Translation: given an input graph, we want to infer a target graph based on their underlying (both global and local) translation mapping. Moreover, by automatically interpreting such translation mapping, we may be able to discover new rules and patterns of the graph translation mechanism. Graph translation could be highly desirable in many applications on network synthesis, such as learning to synthesize the functional connectome from a structural connectome of the brain voxel networks and applications in other domains on network synthesis. To achieve this, we propose a novel Graph-Translation-Generative Adversarial Networks (GT-GAN) which will generate a graph translator from input to target graphs based on adversarial learning. GT-GAN consists of a graph translator where we propose new graph convolution and deconvolution layers to learn the global and local translation mapping. A new conditional graph discriminator has also been proposed to classify target graphs by conditioning on input graphs.

Speaker Bio

Dr. Liang Zhao is an assistant professor at Information Science and Technology Department at George Mason University. He got his PhD degree from Computer Science Department at Virginia Tech in the United States. His research interests include big data mining, artificial intelligence, and machine learning, with particular emphasis on sparse feature learning, social event forecasting, text mining, heterogeneous network modeling, and deep learning on graphs. He got the CRII award from National Science Foundation of United States in 2018. He is named as the one of the “Top 20 Data mining Rising Star in the world” by Microsoft Academic Search in 2016. He has published numerous papers in top venues in data mining and artificial intelligence such as ACM KDD, Proceedings of the IEEE, IEEE TKDE, ACM TKDD, AAAI, IJCAI, IEEE ICDM, ACM CIKM, WWW, and DAC. He has served as publication chair of SSTD 2017, co-chair of LENS workshop at SIGSPATIAL 2018, program committee of ACM KDD 2018, 2019, AAAI 2019, SDM 2019, IEEE ICDM 2017, 2018. He has been serving as reviewer for top conferences and journals such as ACM KDD, ACM TKDD,IEEE TKDE, and IEEE ICDM.