Part 1: Introduction to Graph Learning

In recent years, graph representation of data has become increasingly prevalent across various domains, from social networks to molecular biology. It is crucial to have a deep understanding of Graph Neural Networks (GNNs), which are designed specifically to handle graph-structured data, to unlock the full potential of this representation.

This first part consists of two chapters and serves as a solid foundation for the rest of the book. It introduces the concepts of graph learning and GNNs and their relevance in numerous tasks and industries. It also covers the fundamental concepts of graph theory and its applications in graph learning, such as graph centrality measures. This part also highlights the unique features and performance of the GNN architecture compared to other methods.

By the end of this part, you will have a solid understanding of the importance of GNNs in solving many real-world problems. You will be acquainted with the essentials...