Graph Machine Learning, Second Edition

This is the code repository for Graph Machine Learning, Second Edition, published by Packt.

Learn about the latest advancements in graph data to build robust machine learning models

Aldo Marzullo, Enrico Deusebio, Claudio Stamile

                 

About the book

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 This thoroughly updated edition replaces outdated examples with modern alternatives such as PyTorch and DGL, available on GitHub to support enhanced learning.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.

Key Learnings

• 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

Chapters

Chapters	Colab	Kaggle	Gradient	Studio Lab
Chapter 1: Getting Started with Graphs
01_Introduction_Networkx.ipynb
02_Graph_metrics.ipynb
03_Graphs_Benchmarks.ipynb
Chapter 2: Graph Machine Learning
01_embedding_examples.ipynb
Chapter 3: Neural Networks and Graphs
01_ImageClassification_TensorFlow.ipynb
02_ImageClassification_Pytorch.ipynb
03_Autoencoders.ipynb
04_GraphAutoEncoder_PyGeometric.ipynb
05_GraphAutoEncoder_StellarGraph.ipynb
Chapter 4: Unsupervised Graph Learning
01_Shallow_Embeddings.ipynb
02_Autoencoders.ipynb
03_Structural_deep_neural_embeddings.ipynb
04_Graph_Neural_Network.ipynb
Chapter 5: Supervised Graph Learning
01_Feature_based_methods.ipynb
02_Shallow_embeddings.ipynb
03_Graph_regularization_graph_neural_training.ipynb
04_Graph_Neural_Networks.ipynb
05_Planetoid.ipynb
Chapter 6: Solving Common Graph-Based Machine Learning Problems
01_link_prediction.ipynb
02_community_detection_algorithms.ipynb
03_graph_similarity.ipynb
Chapter 7: Social Network Graphs
01_Social_network_analysis.ipynb
02_Social_network_analysis.ipynb
Chapter 8: Text Analytics and Natural Language Processing Using Graphs
01_nlp_graph_creation.ipynb
02_supervised_classification-embeddings.ipynb
03_supervised_classification_graphSAGE-TFIDF.ipynb
04_supervised_classification_pyg.ipynb
Chapter 9: Graph Analysis for Credit Card Transactions
01_Credit_card_edges_classification.ipynb
Chapter 10: Building a Data-Driven Graph-Powered Application
00_Data_Conversion.ipynb
01_Neo4j_bindings.ipynb
02_JanusGraph_Gremlin.ipynb
Chapter 11: Temporal Graph Machine Learning
Temporal_GraphML.ipynb
Chapter 12: GraphML and LLMs
LLM_and_Graphs.ipynb
Chapter 13: Novel Trends on Graphs

Requirements for this book

We recommend that you use Docker to have a reproducible environment and stable dependency sets. The provided Docker images – one for each chapter – ship with a Jupyter installation and a Python kernel with the dependencies pre-installed, which you can use to run all the examples. For some chapters, Neo4j, JanusGraph, and Gephi are also needed.

Software/Hardware	OS Requirements
Python	Windows, macOS, and Linux (any)
Neo4j	Windows, macOS, and Linux (any)
Gephi	Windows, macOS, and Linux (any)
Docker	Windows, macOS, and Linux (any)

A beginner-level understanding of graph databases and graph data is required. Intermediate-level working knowledge of Python programming and machine learning is also expected to make the most of this book.

The authors acknowledge the use of cutting-edge AI, such as ChatGPT, with the sole aim of enhancing the language and clarity within the book, thereby ensuring a smooth reading experience for readers. It’s important to note that the content itself has been crafted by the authors and edited by a professional publishing team.

Get to know the Authors

Aldo Marzullo received an M.Sc. degree in computer science from the University of Calabria (Cosenza, Italy) in September 2016. During his studies, he developed a solid background in several areas, including algorithm design, graph theory, and machine learning. In January 2020, he received his joint Ph.D. from the University of Calabria and Université Claude Bernard Lyon 1 (Lyon, France), with a thesis titled Deep Learning and Graph Theory for Brain Connectivity Analysis in Multiple Sclerosis. He is currently a postdoctoral researcher and collaborates with several international institutions.

Enrico Deusebio is currently working as engineering manager at Canonical, the publisher of Ubuntu, to promote open source technologies in the data and AI space and to make them more accessible to everyone. He has been working with data and distributed computing for over 15 years, both in an academic and industrial context, helping organizations implement data-driven strategies and build AI-powered solutions. He has collaborated and worked with top-tier universities, such as the University of Cambridge, University of Turin, and the Royal Institute of Technology (KTH) in Stockholm, where he obtained a Ph.D. in 2014. He holds a B.Sc. and an M.Sc. degree in aerospace engineering from Politecnico di Torino.

Claudio Stamile received an M.Sc. degree in computer science from the University of Calabria (Cosenza, Italy) in September 2013 and, in September 2017, he received his joint Ph.D. from KU Leuven (Leuven, Belgium) and Université Claude Bernard Lyon 1 (Lyon, France). During his career, he developed a solid background in AI, graph theory and machine learning with a focus on the biomedical field.

Other Related Books

• Applied Deep Learning on Graphs
• Modern Graph Theory Algorithms with Python