IEEE Services 2020
Tutorial 3
Introduction to Graph Neural Networks

Tutorial 3: Introduction to Graph Neural Networks

Title:	Introduction to Graph Neural Networks
Date/Time:	Monday October 19, 13:00 - 16:00 UTC (21:00 - 24:00 Beijing time)
Summary:	Graphs are a useful and ubiquitous data structure and enormous research efforts have been devoted to graph representation learning recently. Compared to images or text, graphs are typical non-Euclidean data which requires special methods for modeling. Recently, graph neural networks (GNNs) have been proposed to operate on graphs and have achieved promising results in numerous application fields recently. In this tutorial, we provide an introduction to the basic concepts, models, and applications of graph neural networks. The tutorial starts from the vanilla GNN model and followed by its recent variants such as graph convolutional networks, graph recurrent networks, and graph attention networks. Variants designed for different graph types and trained by advanced training methods are also included. In the second part, we will introduce recent applications of GNNs in structural scenarios, non-structural scenarios, and other scenarios. Finally, we will talk about recent advances in self-supervised graph representation learning and our recent work on self-supervised attributed graph embedding. Background required for tutorial attendance: This tutorial is intended for those who are interested in and with little knowledge (but not required) of graph neural networks and graph representation learning. It is better for the audience to have basic background knowledge in deep learning and machine learning.
Speakers:	Zhiyuan Liu, Tsinghua University Zhiyuan Liu is an associate professor at the Department of Computer Science and Technology, Tsinghua University. He received his Ph.D. degree in Computer Science from Tsinghua in 2011. His research interests include representation learning, knowledge graphs and social computation, and has published more than 80 papers in top-tier conferences and journals of AI and NLP including ACL, IJCAI and AAAI, cited by more than 7,800 according to Google Scholar. He is the recipient of the Excellent Doctoral Dissertation of Tsinghua University, the Excellent Doctoral Dissertation of CAAI (Chinese Association for Artificial Intelligence), Outstanding Post-Doctoral Fellow in Tsinghua University, MIT Technology Review Innovators Under 35 China (MIT TR-35 China), BAAI Young Scientist. He serves as Youth Associate Editor of Frontiers of Computer Science, Area Chairs of ACL, EMNLP, COLING, IJCNLP, etc.
	Jie Zhou, Tsinghua University Jie Zhou is a third-year Master’s student of the Department of Computer Science and Technology, Tsinghua University. He got his B.E. from Tsinghua University in 2016. His research interests include graph neural networks and natural language processing.
	Ganqu Cui, Tsinghua University Ganqu Cui is a second year master student of the Department of Computer Science and Technology, Tsinghua University. He received his B.E. degree from Tsinghua University in 2019. His research interests include graph neural networks and network representation learning.