Deep Learning models are at the core of artificial intelligence research today. It is well known that deep learning techniques are disruptive for Euclidean data, such as images or sequence data, and not immediately applicable to graph-structured data such as text. This gap has driven a wave of research for deep learning on graphs, including graph representation learning, graph generation, and graph classification. The new neural network architectures on graph-structured data (graph neural networks, GNNs in short) have performed remarkably on these tasks, demonstrated by applications in social networks, bioinformatics, and medical informatics. Despite these successes, GNNs still face many challenges ranging from the foundational methodologies to the theoretical understandings of the power of the graph representation learning. This book provides a comprehensive introduction of GNNs. It first discusses the goals of graph representation learning and then reviews the history, current developments, and future directions of GNNs. The second part presents and reviews fundamental methods and theories concerning GNNs while the third part describes various frontiers that are built on the GNNs. The book concludes with an overview of recent developments in a number of applications using GNNs. This book is suitable for a wide audience including undergraduate and graduate students, postdoctoral researchers, professors and lecturers, as well as industrial and government practitioners who are new to this area or who already have some basic background but want to learn more about advanced and promising techniques and applications.

Deep Learning models are at the core of artificial intelligence research today. It is well known that deep learning techniques are disruptive for Euclidean data, such as images or sequence data, and not immediately applicable to graph-structured data such as text. This gap has driven a wave of research for deep learning on graphs, including graph representation learning, graph generation, and graph classification. The new neural network architectures on graph-structured data (graph neural networks, GNNs in short) have performed remarkably on these tasks, demonstrated by applications in social networks, bioinformatics, and medical informatics. Despite these successes, GNNs still face many challenges ranging from the foundational methodologies to the theoretical understandings of the power of the graph representation learning. This book provides a comprehensive introduction of GNNs. It first discusses the goals of graph representation learning and then reviews the history, current developments, and future directions of GNNs. The second part presents and reviews fundamental methods and theories concerning GNNs while the third part describes various frontiers that are built on the GNNs. The book concludes with an overview of recent developments in a number of applications using GNNs. This book is suitable for a wide audience including undergraduate and graduate students, postdoctoral researchers, professors and lecturers, as well as industrial and government practitioners who are new to this area or who already have some basic background but want to learn more about advanced and promising techniques and applications.

The two-volume set LNCS 11961 and 11962 constitutes the thoroughly refereed proceedings of the 25th International Conference on MultiMedia Modeling, MMM 2020, held in Daejeon, South Korea, in January 2020. Of the 171 submitted full research papers, 40 papers were selected for oral presentation and 46 for poster presentation; 28 special session papers were selected for oral presentation and 8 for poster presentation; in addition, 9 demonstration papers and 6 papers for the Video Browser Showdown 2020 were accepted. The papers of LNCS 11961 are organized in the following topical sections: audio and signal processing; coding and HVS; color processing and art; detection and classification; face; image processing; learning and knowledge representation; video processing; poster papers; the papers of LNCS 11962 are organized in the following topical sections: poster papers; AI-powered 3D vision; multimedia analytics: perspectives, tools and applications; multimedia datasets for repeatable experimentation; multi-modal affective computing of large-scale multimedia data; multimedia and multimodal analytics in the medical domain and pervasive environments; intelligent multimedia security; demo papers; and VBS papers.