book

Hands-On Graph Neural Networks Using Python

Name: Hands-On Graph Neural Networks Using Python
Author: Maxime Labonne
ISBN: 9781804617526

by Maxime Labonne

April 2023

Intermediate to advanced

354 pages

8h 22m

English

Packt Publishing

Read now

Unlock full access

Hands-On Graph Neural Networks Using Python
ContributorsAbout the authorAbout the reviewers
Preface
Who this book is forWhat this book coversTo get the most out of this bookDownload the example code filesDownload the color imagesConventions usedGet in touchShare your thoughtsDownload a free PDF copy of this book
Part 1: Introduction to Graph Learning
Chapter 1: Getting Started with Graph Learning
Why graphs?Why graph learning?Why graph neural networks?SummaryFurther reading
Chapter 2: Graph Theory for Graph Neural Networks
Technical requirementsIntroducing graph propertiesDirected graphsWeighted graphsConnected graphsTypes of graphsDiscovering graph conceptsFundamental objectsGraph measuresAdjacency matrix representationExploring graph algorithmsBreadth-first searchDepth-first searchSummary
Chapter 3: Creating Node Representations with DeepWalk
Technical requirementsIntroducing Word2VecCBOW versus skip-gramCreating skip-gramsThe skip-gram modelDeepWalk and random walksImplementing DeepWalkSummaryFurther reading
Part 2: Fundamentals
Chapter 4: Improving Embeddings with Biased Random Walks in Node2Vec
Technical requirementsIntroducing Node2VecDefining a neighborhoodIntroducing biases in random walksImplementing Node2VecBuilding a movie RecSysSummaryFurther reading
Chapter 5: Including Node Features with Vanilla Neural Networks
Technical requirementsIntroducing graph datasetsThe Cora datasetThe Facebook Page-Page datasetClassifying nodes with vanilla neural networksClassifying nodes with vanilla graph neural networksSummaryFurther reading
Chapter 6: Introducing Graph Convolutional Networks
Technical requirementsDesigning the graph convolutional layerComparing graph convolutional and graph linear layersPredicting web traffic with node regressionSummaryFurther reading

Chapter 7: Graph Attention Networks
Technical requirementsIntroducing the graph attention layerLinear transformationActivation functionSoftmax normalizationMulti-head attentionImproved graph attention layerImplementing the graph attention layer in NumPyImplementing a GAT in PyTorch GeometricSummary
Part 3: Advanced Techniques
Chapter 8: Scaling Up Graph Neural Networks with GraphSAGE
Technical requirementsIntroducing GraphSAGENeighbor samplingAggregationClassifying nodes on PubMedInductive learning on protein-protein interactionsSummaryFurther reading
Chapter 9: Defining Expressiveness for Graph Classification
Technical requirementsDefining expressivenessIntroducing the GINClassifying graphs using GINGraph classificationImplementing the GINSummaryFurther reading
Chapter 10: Predicting Links with Graph Neural Networks
Technical requirementsPredicting links with traditional methodsHeuristic techniquesMatrix factorizationPredicting links with node embeddingsIntroducing Graph AutoencodersIntroducing VGAEsImplementing a VGAEPredicting links with SEALIntroducing the SEAL frameworkImplementing the SEAL frameworkSummaryFurther reading
Chapter 11: Generating Graphs Using Graph Neural Networks
Technical requirementsGenerating graphs with traditional techniquesThe Erdős–Rényi modelThe small-world modelGenerating graphs with graph neural networksGraph variational autoencodersAutoregressive modelsGenerative adversarial networksGenerating molecules with MolGANSummaryFurther reading
Chapter 12: Learning from Heterogeneous Graphs
Technical requirementsThe message passing neural network frameworkIntroducing heterogeneous graphsTransforming homogeneous GNNs to heterogeneous GNNsImplementing a hierarchical self-attention networkSummaryFurther reading
Chapter 13: Temporal Graph Neural Networks
Technical requirementsIntroducing dynamic graphsForecasting web trafficIntroducing EvolveGCNImplementing EvolveGCNPredicting cases of COVID-19Introducing MPNN-LSTMImplementing MPNN-LSTMSummaryFurther reading
Chapter 14: Explaining Graph Neural Networks
Technical requirementsIntroducing explanation techniquesExplaining GNNs with GNNExplainerIntroducing GNNExplainerImplementing GNNExplainerExplaining GNNs with CaptumIntroducing Captum and integrated gradientsImplementing integrated gradientsSummaryFurther reading
Part 4: Applications
Chapter 15: Forecasting Traffic Using A3T-GCN
Technical requirementsExploring the PeMS-M datasetProcessing the datasetImplementing the A3T-GCN architectureSummaryFurther reading
Chapter 16: Detecting Anomalies Using Heterogeneous GNNs
Technical requirementsExploring the CIDDS-001 datasetPreprocessing the CIDDS-001 datasetImplementing a heterogeneous GNNSummaryFurther reading
Chapter 17: Building a Recommender System Using LightGCN
Technical requirementsExploring the Book-Crossing datasetPreprocessing the Book-Crossing datasetImplementing the LightGCN architectureSummaryFurther reading
Chapter 18: Unlocking the Potential of Graph Neural Networks for Real-World Applications
Index
Why subscribe?
Other Books You May EnjoyPackt is searching for authors like youShare your thoughtsDownload a free PDF copy of this book

Content preview from Hands-On Graph Neural Networks Using Python

4 Improving Embeddings with Biased Random Walks in Node2Vec

Node2Vec is an architecture largely based on DeepWalk. In the previous chapter, we saw the two main components of this architecture: random walks and Word2Vec. How can we improve the quality of our embeddings? Interestingly enough, not with more machine learning. Instead, Node2Vec brings critical modifications to the way random walks themselves are generated.

In this chapter, we will talk about these modifications and how to find the best parameters for a given graph. We will implement the Node2Vec architecture and compare it to using DeepWalk on Zachary’s Karate Club. This will give you a good understanding of the differences between the two architectures. Finally, we will use this ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781804617526

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Hands-On Graph Neural Networks Using Python

by Maxime Labonne

4

Improving Embeddings with Biased Random Walks in Node2Vec

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.