Book Image

Hands-On Graph Neural Networks Using Python

By : Maxime Labonne
Book Image

Hands-On Graph Neural Networks Using Python

By: Maxime Labonne

Overview of this book

Graph neural networks are a highly effective tool for analyzing data that can be represented as a graph, such as networks, chemical compounds, or transportation networks. The past few years have seen an explosion in the use of graph neural networks, with their application ranging from natural language processing and computer vision to recommendation systems and drug discovery. Hands-On Graph Neural Networks Using Python begins with the fundamentals of graph theory and shows you how to create graph datasets from tabular data. As you advance, you’ll explore major graph neural network architectures and learn essential concepts such as graph convolution, self-attention, link prediction, and heterogeneous graphs. Finally, the book proposes applications to solve real-life problems, enabling you to build a professional portfolio. The code is readily available online and can be easily adapted to other datasets and apps. By the end of this book, you’ll have learned to create graph datasets, implement graph neural networks using Python and PyTorch Geometric, and apply them to solve real-world problems, along with building and training graph neural network models for node and graph classification, link prediction, and much more.
Table of Contents (25 chapters)
Part 1: Introduction to Graph Learning
Part 2: Fundamentals
Part 3: Advanced Techniques
Part 4: Applications
Chapter 18: Unlocking the Potential of Graph Neural Networks for Real-World Applications

Getting Started with Graph Learning

Welcome to the first chapter of our journey into the world of graph neural networks (GNNs). In this chapter, we will delve into the foundations of GNNs and understand why they are crucial tools in modern data analysis and machine learning. To that end, we will answer three essential questions that will provide us with a comprehensive understanding of GNNs.

First, we will explore the significance of graphs as a representation of data, and why they are widely used in various domains such as computer science, biology, and finance. Next, we will delve into the importance of graph learning, where we will understand the different applications of graph learning and the different families of graph learning techniques. Finally, we will focus on the GNN family, highlighting its unique features, performance, and how it stands out compared to other methods.

By the end of this chapter, you will have a clear understanding of why GNNs are important and how they can be used to solve real-world problems. You will also be equipped with the knowledge and skills you need to dive deeper into more advanced topics. So, let’s get started!

In this chapter, we will cover the following main topics:

  • Why graphs?
  • Why graph learning?
  • Why graph neural networks?