You're reading from Hands-On Graph Neural Networks Using Python

Product type Book

Published in Apr 2023

Publisher Packt

ISBN-13 9781804617526

Pages 354 pages

Edition 1st Edition

Languages

Concepts

Neural Networks

Author (1):

Maxime Labonne

Table of Contents (25) Chapters

Preface

Part 1: Introduction to Graph Learning

Chapter 1: Getting Started with Graph Learning

Chapter 2: Graph Theory for Graph Neural Networks

Chapter 3: Creating Node Representations with DeepWalk

Part 2: Fundamentals

Chapter 4: Improving Embeddings with Biased Random Walks in Node2Vec

Chapter 5: Including Node Features with Vanilla Neural Networks

Chapter 6: Introducing Graph Convolutional Networks

Chapter 7: Graph Attention Networks

Part 3: Advanced Techniques

Chapter 8: Scaling Up Graph Neural Networks with GraphSAGE

Chapter 9: Defining Expressiveness for Graph Classification

Chapter 10: Predicting Links with Graph Neural Networks

Chapter 11: Generating Graphs Using Graph Neural Networks

Chapter 12: Learning from Heterogeneous Graphs

Chapter 13: Temporal Graph Neural Networks

Chapter 14: Explaining Graph Neural Networks

Part 4: Applications

Chapter 15: Forecasting Traffic Using A3T-GCN

Chapter 16: Detecting Anomalies Using Heterogeneous GNNs

Chapter 17: Building a Recommender System Using LightGCN

Chapter 18: Unlocking the Potential of Graph Neural Networks for Real-World Applications

Index

Why subscribe?

Other Books You May Enjoy

Summary

In this chapter, we defined the expressive power of GNNs. This definition is based on another algorithm, the WL method, which outputs the canonical form of a graph. This algorithm is not perfect, but it can distinguish most graph structures. It inspired the GIN architecture, designed to be as expressive as the WL test and, therefore, strictly more expressive than GCNs, GATs, or GraphSAGE.

We then implemented this architecture for graph classification. We saw different methods to combine node embeddings into graph embeddings. GIN offers a new technique, which incorporates a sum operator and the concatenation of graph embeddings produced by every GIN layer. It significantly outperformed the classic global mean pooling obtained with GCN layers. Finally, we combined predictions made by both models into a simple ensemble, which increased the accuracy score even further.

In Chapter 10, Predicting Links with Graph Neural Networks, we will explore another popular task with GNNs...