| Description |
1 online resource (354 pages) : illustrations |
| Bibliography |
Includes bibliographical references and index. |
| Summary |
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. |
| Contents |
Table of Contents Getting Started with Graph Learning Graph Theory for Graph Neural Networks Creating Node Representations with DeepWalk Improving Embeddings with Biased Random Walks in Node2Vec Including Node Features with Vanilla Neural Networks Introducing Graph Convolutional Networks Graph Attention Networks Scaling Graph Neural Networks with GraphSAGE Defining Expressiveness for Graph Classification Predicting Links with Graph Neural Networks Generating Graphs Using Graph Neural Networks Learning from Heterogeneous Graphs Temporal Graph Neural Networks Explaining Graph Neural Networks Forecasting Traffic Using A3T-GCN Detecting Anomalies Using Heterogeneous Graph Neural Networks Building a Recommender System Using LightGCN Unlocking the Potential of Graph Neural Networks for Real-Word Applications. |
| Subject |
Python (Computer program language)
|
|
Neural networks (Computer science)
|
|
Machine learning.
|
|
Artificial intelligence.
|
|
Python (Langage de programmation) |
|
Réseaux neuronaux (Informatique) |
|
Apprentissage automatique. |
|
Intelligence artificielle. |
|
artificial intelligence. |
|
Artificial intelligence |
|
Machine learning |
|
Neural networks (Computer science) |
|
Python (Computer program language) |
| Other Form: |
Print version: Labonne, Maxime Hands-On Graph Neural Networks Using Python Birmingham : Packt Publishing, Limited,c2023 |
| ISBN |
9781804610701 electronic book |
|
1804610704 electronic book |
|
More Resources