What do you think?
Rate this book
Graph Neural Networks in Action
A hands-on guide to powerful graph-based deep learning models! Learn how to build cutting-edge graph neural networks for recommendation engines, molecular modeling, and more.
In Graph Neural Networks in Actio n, you will learn how
Graph Neural Networks in Action teaches you to create powerful deep learning models for working with graph data. 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. Inside this practical guide, you’ll explore common graph neural network architectures and cutting-edge libraries, all clearly illustrated with well-annotated Python code.
Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.
About the technology
Graph neural networks expand the capabilities of deep learning beyond traditional tabular data, text, and images. This exciting new approach brings the amazing capabilities of deep learning to graph data structures, opening up new possibilities for everything from recommendation engines to pharmaceutical research.
About the book
In Graph Neural Networks in Action you’ll create deep learning models that are perfect for working with interconnected graph data. Start with a comprehensive introduction to graph data’s unique properties. Then, dive straight into building real-world models, including GNNs that can generate node embeddings from a social network, recommend eCommerce products, and draw insights from social sites. This comprehensive guide contains coverage of the essential GNN libraries, including PyTorch Geometric, DeepGraph Library, and Alibaba’s GraphScope for training at scale.
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 machine learning engineer with over ten years executing data science, analytics, and machine learning applications and projects. He is Chief of Machine Learning at candidates.ai, a firm which uses AI to enhance executive search. Dr. Broadwater has delivered DS and ML projects for all types of organizations, from small startups to Fortune 500 companies, and has developed and advised on graph-related projects in the industries of insurance, HR and recruiting, and supply chain.
In Graph Neural Networks in Actio n, you will learn how
Graph Neural Networks in Action teaches you to create powerful deep learning models for working with graph data. 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. Inside this practical guide, you’ll explore common graph neural network architectures and cutting-edge libraries, all clearly illustrated with well-annotated Python code.
Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.
About the technology
Graph neural networks expand the capabilities of deep learning beyond traditional tabular data, text, and images. This exciting new approach brings the amazing capabilities of deep learning to graph data structures, opening up new possibilities for everything from recommendation engines to pharmaceutical research.
About the book
In Graph Neural Networks in Action you’ll create deep learning models that are perfect for working with interconnected graph data. Start with a comprehensive introduction to graph data’s unique properties. Then, dive straight into building real-world models, including GNNs that can generate node embeddings from a social network, recommend eCommerce products, and draw insights from social sites. This comprehensive guide contains coverage of the essential GNN libraries, including PyTorch Geometric, DeepGraph Library, and Alibaba’s GraphScope for training at scale.
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 machine learning engineer with over ten years executing data science, analytics, and machine learning applications and projects. He is Chief of Machine Learning at candidates.ai, a firm which uses AI to enhance executive search. Dr. Broadwater has delivered DS and ML projects for all types of organizations, from small startups to Fortune 500 companies, and has developed and advised on graph-related projects in the industries of insurance, HR and recruiting, and supply chain.
- GenresTechnical
392 pages, Paperback
Published April 15, 2025
5 people are currently reading
17 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 4 of 4 reviews
April 30, 2025
Practical, Insightful, and Production-Ready
A must-read for anyone tackling graph-based ML problems.
This book is a perfect hands-on introduction to Graph Neural Networks. It walks you through real-world applications like node classification and link prediction using clear, annotated PyTorch Geometric code. The balance between practical implementation and essential theory ("Under the Hood" sections) makes it ideal for both engineers and data scientists.
The coverage is broad—embedding, attention, graph autoencoders, and dynamic GNNs—but always focused on building and deploying models. It also helps you evaluate when a GNN is appropriate and when it's not.
Keita Broadwater and Namid Stillman have written the missing manual for applied graph neural networks. With its excellent pedagogy, wide scope, and strong code orientation, Graph Neural Networks in Action is the rare book that bridges the gap between research and practice. If your work involves connected data—or if you're even just GNN-curious—this book deserves a spot on your desk.
Highly recommended.
A must-read for anyone tackling graph-based ML problems.
This book is a perfect hands-on introduction to Graph Neural Networks. It walks you through real-world applications like node classification and link prediction using clear, annotated PyTorch Geometric code. The balance between practical implementation and essential theory ("Under the Hood" sections) makes it ideal for both engineers and data scientists.
The coverage is broad—embedding, attention, graph autoencoders, and dynamic GNNs—but always focused on building and deploying models. It also helps you evaluate when a GNN is appropriate and when it's not.
Keita Broadwater and Namid Stillman have written the missing manual for applied graph neural networks. With its excellent pedagogy, wide scope, and strong code orientation, Graph Neural Networks in Action is the rare book that bridges the gap between research and practice. If your work involves connected data—or if you're even just GNN-curious—this book deserves a spot on your desk.
Highly recommended.
April 25, 2025
Serves as a great starting point for readers who might view graph neural networks as theoretically daunting. "Graph Neural Networks in Action" provides a pragmatic introduction with a structured progression that bridges theory and practice through hands-on applications that direct readers through application of GNNs directly to their own projects. The book is accessible to newcomers and makes a good 1-2 punch with "Graph-Powered Machine Learning" from the same publisher. Afterwards, I recommend William Hamilton's "Graph Representation Learning" to fill out theoretical details.
Read
April 16, 2025Practical and accessible introduction to GNNs, aimed at developers with experience in deep learning. It offers concrete examples, great for looking to move from theory to implementation.
August 2, 2025
The most intuitive book i have ever read about GNN. Lots of code implementations that i can reproduce on my future use case leveraging GNN. i am impressed by how the author structures each chapter well that really help me follow along the terms. It is gonna be my go-to resources.
Displaying 1 - 4 of 4 reviews