Beschreibung:
Chapter 1. Representation Learning -- Chapter 2. Graph Representation Learning -- Chapter 3. Graph Neural Networks -- Chapter 4. Graph Neural Networks for Node Classification -- Chapter 5. The Expressive Power of Graph Neural Networks -- Chapter 6. Graph Neural Networks: Scalability -- Chapter 7. Interpretability in Graph Neural Networks -- Chapter 8. "Graph Neural Networks: Adversarial Robustness" -- Chapter 9. Graph Neural Networks: Graph Classification -- Chapter 10. Graph Neural Networks: Link Prediction -- Chapter 11. Graph Neural Networks: Graph Generation -- Chapter 12. Graph Neural Networks: Graph Transformation -- Chapter 13. Graph Neural Networks: Graph Matching -- Chapter 14. "Graph Neural Networks: Graph Structure Learning". Chapter 15. Dynamic Graph Neural Networks -- Chapter 16. Heterogeneous Graph Neural Networks -- Chapter 17. Graph Neural Network: AutoML -- Chapter 18. Graph Neural Networks: Self-supervised Learning -- Chapter 19. Graph Neural Network in Modern Recommender Systems -- Chapter 20. Graph Neural Network in Computer Vision -- Chapter 21. Graph Neural Networks in Natural Language Processing -- Chapter 22. Graph Neural Networks in Program Analysis -- Chapter 23. Graph Neural Networks in Software Mining -- Chapter 24. "GNN-based Biomedical Knowledge Graph Mining in Drug Development" -- Chapter 25. "Graph Neural Networks in Predicting Protein Function and Interactions" -- Chapter 26. Graph Neural Networks in Anomaly Detection -- Chapter 27. Graph Neural Networks in Urban Intelligence. .
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.