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

Defining expressiveness

Neural networks are used to approximate functions. This is justified by the universal approximation theorem, which states that a feedforward neural network with only one layer can approximate any smooth function. But what about universal function approximation on graphs? This is a more complex problem that requires the ability to distinguish graph structures.

With GNNs, our goal is to produce the best node embeddings possible. This means that different nodes must have different embeddings, and similar nodes must have similar embeddings. But how do we know that two nodes are similar? Embeddings are computed using node features and connections. Therefore, we have to compare their features and neighbors to distinguish nodes.

In graph theory, this is referred to as the graph isomorphism problem. Two graphs are isomorphic (“the same”) if they have the same connections, and their only difference is a permutation of their nodes (see Figure 9.1)...