Graph Neural Networks in Action

В этом материале разберём тему: data.

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.

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. About the bookGraph Neural Networks in Action teaches you how to analyze and make predictions on data structured as graphs. 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 insideTrain and deploy a graph neural networkGenerate node embeddingsUse GNNs for very large datasetsBuild a graph data pipelineAbout the readerFor Python programmers familiar with machine learning and the basics of deep learning.

Если материал оказался полезен — сохраните страницу.