A practical guide to powerful graph-based deep learning models!

Graph Neural Networks in Action is a comprehensive guide on how to build cutting-edge graph neural networks and powerful deep learning models for recommendation systems, molecular modeling, and more.

Learn how to design and train your models, and how to develop them into practical applications you can deploy to production. Ideal for Python programmers, you'll also explore common graph neural network architectures and state-of-the-art libraries, all clearly illustrated with well-annotated Python code.

The main features include:

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

Get hands-on experience and explore relevant real-world projects as you dive into graph neural networks suitable for node prediction, link prediction, and graph classification.

About the technology: Graph neural networks extend the capabilities of deep learning beyond traditional tabular data, text, and images. This exciting new approach brings the incredible power of deep learning to graph data structures, opening up new opportunities for everything from recommendation engines to pharmaceutical research.

Pages: 350, Dimensions: 18.7x18.7cm