Ma Y., Tang J. Deep Learning on Graphs 2021

Textbook in PDF format

This book covers comprehensive contents in developing deep learning techniques for graph structured data with a specific focus on Graph Neural Networks (GNNs). The foundation of the GNN models are introduced in detail including the two main building operations: graph filtering and pooling operations. We then discuss the robustness and scalability of the GNNs, which are extremely important for utilizing GNNs for real-world applications. To enable deep learning techniques to advance more graph tasks under wider settings, we introduce numerous deep graph models beyond GNNs. We also present the most representative applications of GNNs in different areas such as Natural Language Processing, Computer Vision, Data Mining and Healthcare. The book is also self-contained, we include chapters for introducing some basics on graphs and also on deep learning. We conclude the book with recent advances of GNNs in both methods and applications