Advances in Graph Neural Networks

ISBN-13: 9783031161735 / Angielski / Twarda / 2022 / 198 str.

Chuan Shi; Xiao Wang; Cheng Yang

Opis

This book provides a comprehensive introduction to the foundations and frontiers of graph neural networks. In addition, the book introduces the basic concepts and definitions in graph representation learning and discusses the development of advanced graph representation learning methods with a focus on graph neural networks. The book providers researchers and practitioners with an understanding of the fundamental issues as well as a launch point for discussing the latest trends in the science. The authors emphasize several frontier aspects of graph neural networks and utilize graph data to describe pairwise relations for real-world data from many different domains, including social science, chemistry, and biology. Several frontiers of graph neural networks are introduced, which enable readers to acquire the needed techniques of advances in graph neural networks via theoretical models and real-world applications. 

Spis treści

Introduction.- Fundamental Graph Neural Networks.- Homogeneous Graph Neural Networks.- Heterogeneous Graph Neural Networks.- Dynamic Graph Neural Networks.- Hyperbolic Graph Neural Networks.- Distilling Graph Neural Networks.-  Platforms and Practice of Graph Neural Networks.- Future Direction and Conclusion.- References. 

 

O autorze

Chuan Shi, PhD., is a Professor and Deputy Director of Beijing Key Lab of Intelligent Telecommunications Software and Multimedia at the Beijing University of Posts and Telecommunications.  He received his B.S. from Jilin University in 2001, his M.S. from Wuhan University in 2004, and his Ph.D. from the ICT of Chinese Academic of Sciences in 2007.  His research interests include data mining, machine learning, and evolutionary computing. He has published more than 100 papers in refereed journals and conferences.

Xiao Wang, Ph.D., is an Associate Professor in the School of Computer Science at the Beijing University of Posts and Telecommunications. He received his Ph.D. from the School of Computer Science and Technology at Tianjin University in 2016. He was a postdoctoral researcher in the Department of Computer Science and Technology at Tsinghua University.  His current research interests include data mining, social network analysis, and machine learning. He has published more than 70 papers in refereed journals and conferences.

Cheng Yang, Ph.D., is an Associate Professor at the Beijing University of Posts and Telecommunications. He received his B.E. and Ph.D. from Tsinghua University in 2014 and 2019, respectively. His research interests include natural language processing and network representation learning. He has published more than 20 top-level papers in international journals and conferences including ACM TOIS, EMNLP, IJCAI, and AAAI.

Blurb

This book provides a comprehensive introduction to the foundations and frontiers of graph neural networks. In addition, the book introduces the basic concepts and definitions in graph representation learning and discusses the development of advanced graph representation learning methods with a focus on graph neural networks. The book providers researchers and practitioners with an understanding of the fundamental issues as well as a launch point for discussing the latest trends in the science. The authors emphasize several frontier aspects of graph neural networks and utilize graph data to describe pairwise relations for real-world data from many different domains, including social science, chemistry, and biology. Several frontiers of graph neural networks are introduced, which enable readers to acquire the needed techniques of advances in graph neural networks via theoretical models and real-world applications.

In addition, this book:

• Provides a comprehensive introduction to the foundations and frontiers of graph neural networks and also summarizes the basic concepts and terminology in graph modeling
• Utilizes graph data to describe pairwise relations for real-world data from many different domains, including social science, chemistry, and biology
• Presents heterogeneous graph representation learning alongside homogeneous graph representation and Euclidean graph neural networks methods