Graph Machine Learning : Learn about the Latest Advancements in Graph Data to Build Robust Machine Learning Algorithms.

Format:

Book

Author/Creator:

Marzullo, Aldo.

Contributor:

Deusebio, Enrico.

Stamile, Claudio.

Language:

English

Subjects (All):

Machine learning.

Graph theory--Data processing.

Graph theory.

Physical Description:

1 online resource (0 pages)

Edition:

1st ed.

Place of Publication:

Birmingham : Packt Publishing, Limited, 2025.

Summary:

Enhance your data science skills with this updated edition featuring new chapters on LLMs, temporal graphs, and updated examples with modern frameworks, including PyTorch Geometric, and DGL Key Features Master new graph ML techniques through updated examples using PyTorch Geometric and Deep Graph Library (DGL) Explore GML frameworks and their main characteristics Leverage LLMs for machine learning on graphs and learn about temporal learning Purchase of the print or Kindle book includes a free PDF eBook Book Description Graph Machine Learning, Second Edition builds on its predecessor's success, delivering the latest tools and techniques for this rapidly evolving field. From basic graph theory to advanced ML models, you'll learn how to represent data as graphs to uncover hidden patterns and relationships, with practical implementation emphasized through refreshed code examples. This thoroughly updated edition replaces outdated examples with modern alternatives such as PyTorch and DGL, available on GitHub to support enhanced learning.The book also introduces new chapters on large language models and temporal graph learning, along with deeper insights into modern graph ML frameworks. Rather than serving as a step-by-step tutorial, it focuses on equipping you with fundamental problem-solving approaches that remain valuable even as specific technologies evolve. You will have a clear framework for assessing and selecting the right tools.By the end of this book, you'll gain both a solid understanding of graph machine learning theory and the skills to apply it to real-world challenges. What you will learn Implement graph ML algorithms with examples in StellarGraph, PyTorch Geometric, and DGL Apply graph analysis to dynamic datasets using temporal graph ML Enhance NLP and text analytics with graph-based techniques Solve complex real-world problems with graph machine learning Build and scale graph-powered ML applications effectively Deploy and scale your application seamlessly Who this book is for This book is for data scientists, ML professionals, and graph specialists looking to deepen their knowledge of graph data analysis or expand their machine learning toolkit. Prior knowledge of Python and basic machine learning principles is recommended. ]]>

Contents:

Cover

FM

Copyright

Contributors

Table of Contents

Preface

Introduction to Graph Machine Learning

Chapter 1: Getting Started with Graphs

Practical exercises

Conventions

Technical requirements

Introduction to graphs with networkx

Types of graphs

Digraphs

Multigraph

Weighted graphs

Multipartite graphs

Connected graphs

Disconnected graphs

Complete graphs

Graph representations

Adjacency matrix

Edge list

Plotting graphs

NetworkX

Gephi

Graph properties

Integration metrics

Distance, path, and shortest path

Characteristic path length

Global and local efficiency

Segregation metrics

Clustering coefficient

Modularity

Centrality metrics

Degree centrality

Closeness centrality

Betweenness centrality

Resilience metrics

Assortativity coefficient

Hands-on examples

Simple graphs

Generative graph models

Watts and Strogatz (1998)

Barabási-Albert (1999)

Data resources for network analysis

Network Repository

Stanford Large Network Dataset Collection

Open Graph Benchmark

Dealing with large graphs

Summary

Chapter 2: Graph Machine Learning

Understanding machine learning on graphs

Basic principles of machine learning

The benefit of machine learning on graphs

The generalized graph embedding problem

The taxonomy of graph embedding machine learning algorithms

Chapter 3: Neural Networks and Graphs

Introduction to ANNs

Training neural networks

Computational frameworks for ANNs

TensorFlow

A simple classification example

PyTorch

Classification beyond fully connected layers

Introduction to GNNs

Variants of GNNs

Frameworks for deep learning on graphs

Graph representation.

Data loading

Model definition

Training loop

PyG

StellarGraph

DGL

Machine Learning on Graphs

Chapter 4: Unsupervised Graph Learning

The unsupervised graph embedding roadmap

Shallow embedding methods

Matrix factorization

Graph factorization

Higher-order proximity preserved embedding

Graph representation with global structure information

Skip-gram

DeepWalk

Node2Vec

Edge2Vec

Graph2Vec

Autoencoders

Our first autoencoder

Denoising autoencoders

Graph autoencoders

Graph neural networks

Spectral graph convolution

Spatial graph convolution

Graph convolution in practice

Chapter 5: Supervised Graph Learning

The supervised graph embedding roadmap

Feature-based methods

Label propagation algorithm

Label spreading algorithm

Graph regularization methods

Manifold regularization and semi-supervised embedding

Neural graph learning

Planetoid

Graph CNNs

Graph classification using GCNs

Node classification using GraphSAGE

Chapter 6: Solving Common Graph-Based Machine Learning Problems

Predicting missing links in a graph

Similarity-based methods

Index-based methods

Resource allocation index

Jaccard coefficient

Community-based methods

Community common neighbor

Community resource allocation

Embedding-based methods

Detecting meaningful structures such as communities

Embedding-based community detection

Spectral methods and matrix factorization

Probability models

Cost function minimization

Detecting graph similarities and graph matching

Graph embedding-based methods

Graph kernel-based methods

GNN-based methods

Applications

Summary.

Practical Applications of Graph Machine Learning

Chapter 7: Social Network Graphs

Overview of the dataset

Dataset download

Loading the dataset using networkx

Analyzing the graph structure

Topology overview

Node centrality

Community detection

Embedding for supervised and unsupervised tasks

Task preparation

Node2Vec-based link prediction

GraphSAGE-based link prediction

Featureless approach

Introducing node features

Hand-crafted features for link prediction

Summarizing the results

Chapter 8: Text Analytics and Natural Language Processing Using Graphs

Providing a quick overview of a dataset

Understanding the main concepts and tools used in NLP

Creating graphs from a corpus of documents

Knowledge graphs

Bipartite document/entity graphs

Entity-entity graph

Filtering the graph: Be aware of dimensions

Analyzing the graph

Document-document graph

Building a document topic classifier

Shallow-learning methods

Graph neural network

Chapter 9: Graph Analysis for Credit Card Transactions

Building graphs from credit card transactions

Loading the dataset

Building the graphs using networkx

Network topology and community detection

Network topology

Applying supervised and unsupervised fraud approaches to fraud detection

Dataset resampling

Node feature generation

Training and evaluating the model

Hyperparameter tuning

Unsupervised approach to fraudulent transaction identification

Additional resources

Chapter 10: Building a Data-Driven Graph-Powered Application

Overview of Lambda architecture

Lambda architectures for graph-powered applications.

Graph querying engine

Neo4j

JanusGraph - a graph database to scale out to very large datasets

Graph processing engines

Selecting the right technology

Advanced topics in Graph Machine Learning

Chapter 11: Temporal Graph Machine Learning

What are dynamic graphs?

Common problems with temporal graphs

Representing dynamic graphs

Embedding dynamic graphs

Factorization-based methods

Random walk-based methods

Temporal point process methods

Deep learning-based methods

Agnostic methods

Hands-on temporal graphs

Temporal matrix factorization

Temporal random walk

TGNNs

Further reading

Chapter 12: GraphML and LLMs

LLMs: an overview

Why combine GraphML with LLMs?

State-of-the-art trends and challenges

LLMs as predictors

LLMs as encoders

LLMs as aligners

Hands-on GraphML with LLMs

LLM as predictor

LLM as encoder

LLM as aligner

Building knowledge graphs from text

Real-world scenarios: GraphRAG

Challenges and future directions

Chapter 13: Novel Trends on Graphs

Data augmentation for graphs

Sampling strategies

Exploring data augmentation techniques

Learning about topological data analysis

Topological machine learning

Applying graph theory in new domains

Graph machine learning and neuroscience

Graph theory and chemistry and biology

Graph machine learning and computer vision

Image classification and scene understanding

Shape analysis

Recommendation systems

Graph machine learning and NLP

Index

Other Books You May Enjoy.

Notes:

Description based upon print version of record.

Description based on publisher supplied metadata and other sources.

ISBN:

1-80324-661-8

OCLC:

1525621075