0%

Build machine learning algorithms using graph data and efficiently exploit topological information within your models

Key Features

  • Implement machine learning techniques and algorithms in graph data
  • Identify the relationship between nodes in order to make better business decisions
  • Apply graph-based machine learning methods to solve real-life problems

Book Description

Graph Machine Learning provides a new set of tools for processing network data and leveraging the power of the relation between entities that can be used for predictive, modeling, and analytics tasks.

You will start with a brief introduction to graph theory and graph machine learning, understanding their potential. As you proceed, you will become well versed with the main machine learning models for graph representation learning: their purpose, how they work, and how they can be implemented in a wide range of supervised and unsupervised learning applications. You'll then build a complete machine learning pipeline, including data processing, model training, and prediction in order to exploit the full potential of graph data. Moving ahead, you will cover real-world scenarios such as extracting data from social networks, text analytics, and natural language processing (NLP) using graphs and financial transaction systems on graphs. Finally, you will learn how to build and scale out data-driven applications for graph analytics to store, query, and process network information, before progressing to explore the latest trends on graphs.

By the end of this machine learning book, you will have learned essential concepts of graph theory and all the algorithms and techniques used to build successful machine learning applications.

What you will learn

  • Write Python scripts to extract features from graphs
  • Distinguish between the main graph representation learning techniques
  • Become well-versed with extracting data from social networks, financial transaction systems, and more
  • Implement the main unsupervised and supervised graph embedding techniques
  • Get to grips with shallow embedding methods, graph neural networks, graph regularization methods, and more
  • Deploy and scale out your application seamlessly

Who this book is for

This book is for data analysts, graph developers, graph analysts, and graph professionals who want to leverage the information embedded in the connections and relations between data points to boost their analysis and model performance. The book will also be useful for data scientists and machine learning developers who want to build ML-driven graph databases. 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 out of this book.

Table of Contents

  1. Graph Machine Learning
  2. Contributors
  3. About the authors
  4. About the reviewers
  5. Preface
    1. Who this book is for
    2. What this book covers
    3. To get the most out of this book
    4. Download the example code files
    5. Download the color images
    6. Conventions used
    7. Get in touch
    8. Reviews
  6. Section 1 – Introduction to Graph Machine Learning
  7. Chapter 1: Getting Started with Graphs
    1. Technical requirements
    2. Introduction to graphs with networkx
    3. Types of graphs
    4. Graph representations
    5. Plotting graphs
    6. networkx
    7. Gephi
    8. Graph properties
    9. Integration metrics
    10. Segregation metrics
    11. Centrality metrics
    12. Resilience metrics
    13. Benchmarks and repositories
    14. Examples of simple graphs
    15. Generative graph models
    16. Benchmarks
    17. Dealing with large graphs
    18. Summary 
  8. Chapter 2: Graph Machine Learning
    1. Technical requirements
    2. Understanding machine learning on graphs
    3. Basic principles of machine learning
    4. The benefit of machine learning on graphs
    5. The generalized graph embedding problem
    6. The taxonomy of graph embedding machine learning algorithms
    7. The categorization of embedding algorithms
    8. Summary 
  9. Section 2 – Machine Learning on Graphs
  10. Chapter 3: Unsupervised Graph Learning
    1. Technical requirements
    2. The unsupervised graph embedding roadmap
    3. Shallow embedding methods
    4. Matrix factorization
    5. Skip-gram
    6. Autoencoders
    7. TensorFlow and Keras – a powerful combination
    8. Our first autoencoder
    9. Denoising autoencoders
    10. Graph autoencoders
    11. Graph neural networks
    12. Variants of GNNs
    13. Spectral graph convolution
    14. Spatial graph convolution
    15. Graph convolution in practice
    16. Summary 
  11. Chapter 4: Supervised Graph Learning
    1. Technical requirements
    2. The supervised graph embedding roadmap 
    3. Feature-based methods 
    4. Shallow embedding methods 
    5. Label propagation algorithm
    6. Label spreading algorithm
    7. Graph regularization methods
    8. Manifold regularization and semi-supervised embedding
    9. Neural Graph Learning
    10. Planetoid
    11. Graph CNNs
    12. Graph classification using GCNs
    13. Node classification using GraphSAGE
    14. Summary 
  12. Chapter 5: Problems with Machine Learning on Graphs
    1. Technical requirements
    2. Predicting missing links in a graph
    3. Similarity-based methods
    4. Embedding-based methods
    5. Detecting meaningful structures such as communities
    6. Embedding-based community detection
    7. Spectral methods and matrix factorization
    8. Probability models
    9. Cost function minimization
    10. Detecting graph similarities and graph matching
    11. Graph embedding-based methods
    12. Graph kernel-based methods
    13. GNN-based methods
    14. Applications
    15. Summary 
  13. Section 3 – Advanced Applications of Graph Machine Learning
  14. Chapter 6: Social Network Graphs
    1. Technical requirements
    2. Overview of the dataset
    3. Dataset download
    4. Loading the dataset using networkx
    5. Network topology and community detection
    6. Topology overview
    7. Node centrality
    8. Community detection
    9. Embedding for supervised and unsupervised tasks
    10. Task preparation
    11. node2vec-based link prediction
    12. GraphSAGE-based link prediction
    13. Hand-crafted features for link prediction
    14. Summary of results
    15. Summary
  15. Chapter 7: Text Analytics and Natural Language Processing Using Graphs
    1. Technical requirements
    2. Providing a quick overview of a dataset
    3. Understanding the main concepts and tools used in NLP
    4. Creating graphs from a corpus of documents
    5. Knowledge graphs
    6. Bipartite document/entity graphs
    7. Building a document topic classifier
    8. Shallow learning methods
    9. Graph neural networks
    10. Summary
  16. Chapter 8:Graph Analysis for Credit Card Transactions
    1. Technical requirements
    2. Overview of the dataset
    3. Loading the dataset and graph building using networkx
    4. Network topology and community detection
    5. Network topology
    6. Community detection
    7. Embedding for supervised and unsupervised fraud detection
    8. Supervised approach to fraudulent transaction identification
    9. Unsupervised approach to fraudulent transaction identification
    10. Summary
  17. Chapter 9: Building a Data-Driven Graph-Powered Application
    1. Technical requirements
    2. Overview of Lambda architectures
    3. Lambda architectures for graph-powered applications
    4. Graph processing engines
    5. Graph querying layer
    6. Selecting between Neo4j and GraphX
    7. Summary
  18. Chapter 10: Novel Trends on Graphs
    1. Technical requirements 
    2. Learning about data augmentation for graphs
    3. Sampling strategies
    4. Exploring data augmentation techniques
    5. Learning about topological data analysis
    6. Topological machine learning
    7. Applying graph theory in new domains
    8. Graph machine learning and neuroscience
    9. Graph theory and chemistry and biology
    10. Graph machine learning and computer vision
    11. Recommendation systems
    12. Summary
    13. Why subscribe?
  19. Other Books You May Enjoy
    1. Packt is searching for authors like you
    2. Leave a review - let other readers know what you think
54.81.157.133