Graph Neural Networks in Action

A hands-on guide to powerful graph-based deep learning models.

Graph Neural Networks in Action teaches you to build cutting-edge graph neural networks for recommendation engines, molecular modeling, and more. This comprehensive guide contains coverage of the essential GNN libraries, including PyTorch Geometric, DeepGraph Library, and Alibaba's GraphScope for training at scale.

In Graph Neural Networks in Action, you will learn how to:

- Train and deploy a graph neural network
- Generate node embeddings
- Use GNNs at scale for very large datasets
- Build a graph data pipeline
- Create a graph data schema
- Understand the taxonomy of GNNs
- Manipulate graph data with NetworkX

In Graph Neural Networks in Action you'll learn how to both design and train your models, and how to develop them into practical applications you can deploy to production. Go hands-on and explore relevant real-world projects as you dive into graph neural networks perfect for node prediction, link prediction, and graph classification.

Foreword by Matthias Fey.

Purchase of the print book includes a free eBook in PDF and ePub formats from Manning Publications.

About the technology

Graphs are a natural way to model the relationships and hierarchies of real-world data. Graph neural networks (GNNs) optimize deep learning for highly-connected data such as in recommendation engines and social networks, along with specialized applications like molecular modeling for drug discovery.

About the book

Graph Neural Networks in Action teaches you how to analyze and make predictions on data structured as graphs. You'll work with graph convolutional networks, attention networks, and auto-encoders to take on tasks like node classification, link prediction, working with temporal data, and object classification. Along the way, you'll learn the best methods for training and deploying GNNs at scale--all clearly illustrated with well-annotated Python code!

What's inside

- Train and deploy a graph neural network
- Generate node embeddings
- Use GNNs for very large datasets
- Build a graph data pipeline

About the reader

For Python programmers familiar with machine learning and the basics of deep learning.

About the author

Keita Broadwater, PhD, MBA is a seasoned machine learning engineer. Namid Stillman, PhD is a research scientist and machine learning engineer with more than 20 peer-reviewed publications.

Table of Contents

Part 1
1 Discovering graph neural networks
2 Graph embeddings
Part 2
3 Graph convolutional networks and GraphSAGE
4 Graph attention networks
5 Graph autoencoders
Part 3
6 Dynamic graphs: Spatiotemporal GNNs
7 Learning and inference at scale
8 Considerations for GNN projects
A Discovering graphs
B Installing and configuring PyTorch Geometric