9.3 Graphs with Edge Information
10 Variants for Advanced Training Methods
11.1 Message Passing Neural Networks
11.2 Non-local Neural Networks
12 Applications – Structural Scenarios
12.2.2 Chemical Reaction Prediction
12.2.3 Medication Recommendation
12.2.4 Protein and Molecular Interaction Prediction
12.3.1 Knowledge Graph Completion
12.3.2 Inductive Knowledge Graph Embedding
12.3.3 Knowledge Graph Alignment
13 Applications – Non-Structural Scenarios
13.2.3 Neural Machine Translation
14 Applications – Other Scenarios
14.2 Combinatorial Optimization
Preface
Deep learning has achieved promising progress in many fields such as computer vision and natural language processing. The data in these tasks are usually represented in the Euclidean domain. However, many learning tasks require dealing with non-Euclidean graph data that contains rich relational information between elements, such as modeling physical systems, learning molecular fingerprints, predicting protein interface, etc. Graph neural networks (GNNs) are deep learning-based methods that operate on graph domains. Due to its convincing performance and high interpretability, GNN has recently been a widely applied graph analysis method.
The book provides a comprehensive introduction to the basic concepts, models, and applications of graph neural networks. It starts with the basics of mathematics and neural networks. In the first chapters, it gives an introduction to the basic concepts of GNNs, which aims to provide a general overview for readers. Then it introduces different variants of GNNs: graph convolutional networks, graph recurrent
