نکته: این کتاب در برخی از صفحات دارای نمودارهای رنگی هست که در چاپ سیاه و سفید قابل تشخیص نیست. ترجیحا رنگی سفارش داده شود.

Design robust graph neural networks with PyTorch Geometric by combining graph theory and neural networks with the latest developments and apps

Key Features

• Implement state-of-the-art graph neural network architectures in Python
• Create your own graph datasets from tabular data
• Build powerful traffic forecasting, recommender systems, and anomaly detection applications

Book Description

Graph neural networks are a highly effective tool for analyzing data that can be represented as a graph, such as social 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.

What you will learn

• Understand the fundamental concepts of graph neural networks
• Implement graph neural networks using Python and PyTorch Geometric
• Classify nodes, graphs, and edges using millions of samples
• Predict and generate realistic graph topologies
• Combine heterogeneous sources to improve performance
• Forecast future events using topological information
• Apply graph neural networks to solve real-world problems

Who this book is for

This book is for machine learning practitioners and data scientists interested in learning about graph neural networks and their applications, as well as students looking for a comprehensive reference on this rapidly growing field. Whether you're new to graph neural networks or looking to take your knowledge to the next level, this book has something for you. Basic knowledge of machine learning and Python programming will help you get the most out of this book.

Table of Contents

1. Getting Started with Graph Learning
2. Graph Theory for Graph Neural Networks
3. Creating Node Representations with DeepWalk
4. Improving Embeddings with Biased Random Walks in Node2Vec
5. Including Node Features with Vanilla Neural Networks
6. Introducing Graph Convolutional Networks
7. Graph Attention Networks
8. Scaling Graph Neural Networks with GraphSAGE
9. Defining Expressiveness for Graph Classification
10. Predicting Links with Graph Neural Networks
11. Generating Graphs Using Graph Neural Networks
12. Learning from Heterogeneous Graphs
13. Temporal Graph Neural Networks
14. Explaining Graph Neural Networks
15. Forecasting Traffic Using A3T-GCN
16. Detecting Anomalies Using Heterogeneous Graph Neural Networks
17. Building a Recommender System Using LightGCN
18. Unlocking the Potential of Graph Neural Networks for Real-Word Applications

About the Author

Maxime Labonne is currently a senior applied researcher at Airbus. He received a M.Sc. degree in computer science from INSA CVL, and a Ph.D. in machine learning and cyber security from the Polytechnic Institute of Paris. During his career, he worked on computer networks and the problem of representation learning, which led him to explore graph neural networks. He applied this knowledge to various industrial projects, including intrusion detection, satellite communications, quantum networks, and AI-powered aircrafts. He is now an active graph neural network evangelist through Twitter and his personal blog.