What this book covers

Chapter 1, Getting Started with Graphs, introduces the basic concepts of graph theory using the NetworkX Python library.

Chapter 2, Graph Machine Learning, introduces the main concepts of graph machine learning and graph embedding techniques.

Chapter 3, Neural Networks and Graphs, introduces Graph Neural Networks (GNNs) and the leading libraries for graph-based deep learning.

Chapter 4, Unsupervised Graph Learning, covers recent unsupervised graph embedding methods.

Chapter 5, Supervised Graph Learning, covers recent supervised graph embedding methods.

Chapter 6, Solving Common Graph-Based Machine Learning Problems, introduces the most common machine learning tasks on graphs.

Chapter 7, Social Network Graphs, shows an application of machine learning algorithms on social network data.

Chapter 8, Text Analytics and Natural Language Processing Using Graphs, shows an application of machine learning algorithms on a natural language processing task.

Chapter 9, Graphs Analysis for Credit Card Transactions, shows an application of machine learning algorithms in credit card fraud detection.

Chapter 10, Building a Data-Driven Graph-Powered Application, introduces some technologies and techniques useful to deal with large graphs.

Chapter 11, Temporal Graph Machine Learning, focuses on techniques to model and learn from dynamic, time-evolving graph data.

Chapter 12, GraphML and LLMs, explores how graph structures can enhance LLMs and how LLMs can be used for graph-based tasks.

Chapter 13, Novel Trends on Graphs, introduces some novel trends (algorithms and applications) of graph machine learning.