Graph Machine Learning: Take graph data to the next level by applying machine learning techniques and algorithms

Description

Build machine learning algorithms using graph data and efficiently exploit topological information within your models Key FeaturesImplement machine learning techniques and algorithms in graph dataIdentify the relationship between nodes in order to make better business decisionsApply graph-based machine learning methods to solve real-life problemsBook 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 learnWrite Python scripts to extract features from graphsDistinguish between the main graph representation learning techniquesBecome well-versed with extracting data from social networks, financial transaction systems, and moreImplement the main unsupervised and supervised graph embedding techniquesGet to grips with shallow embedding methods, graph neural networks, graph regularization methods, and moreDeploy and scale out your application seamlesslyWho this book is for This book is for data scientists, data analysts, 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 using machine learning. The book will also be useful for machine learning developers or anyone 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 ContentsGetting Started with GraphsGraph Machine LearningUnsupervised Graph LearningSupervised Graph LearningProblems with Machine Learning on GraphsSocial Network GraphsText Analytics and Natural Language Processing Using GraphsGraph Analysis for Credit Card TransactionsBuilding a Data-Driven Graph-Powered ApplicationNovel Trends on Graphs Cover Title Page Copyright and Credits Dedication Contributors Table of Contents Preface Section 1 – Introduction to Graph Machine Learning Chapter 1: Getting Started with Graphs Technical requirements Introduction to graphs with networkx Types of graphs Graph representations Plotting graphs networkx Gephi Graph properties Integration metrics Segregation metrics Centrality metrics Resilience metrics Benchmarks and repositories Examples of simple graphs Generative graph models Benchmarks Dealing with large graphs Summary  Chapter 2: Graph Machine Learning Technical requirements 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 The categorization of embedding algorithms Summary  Section 2 – Machine Learning on Graphs Chapter 3: Unsupervised Graph Learning Technical requirements The unsupervised graph embedding roadmap Shallow embedding methods Matrix factorization Skip-gram Autoencoders TensorFlow and Keras – a powerful combination Our first autoencoder Denoising autoencoders Graph autoencoders Graph neural networks Variants of GNNs Spectral graph convolution Spatial graph convolution Graph convolution in practice Summary  Chapter 4: Supervised Graph Learning Technical requirements The supervised graph embedding roadmap  Feature-based methods  Shallow embedding 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 Summary  Chapter 5: Problems with Machine Learning on Graphs Technical requirements Predicting missing links in a graph Similarity-based methods 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  Section 3 – Advanced Applications of Graph Machine Learning Chapter 6: Social Network Graphs Technical requirements Overview of the dataset Dataset download Loading the dataset using networkx Network topology and community detection Topology overview Node centrality Community detection Embedding for supervised and unsupervised tasks Task preparation node2vec-based link prediction GraphSAGE-based link prediction Hand-crafted features for link prediction Summary of results Summary Chapter 7: Text Analytics and Natural Language Processing Using Graphs Technical requirements 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 Building a document topic classifier Shallow learning methods Graph neural networks Summary Chapter 8: Graph Analysis for Credit Card Transactions Technical requirements Overview of the dataset Loading the dataset and graph building using networkx Network topology and community detection Network topology Community detection Embedding for supervised and unsupervised fraud detection Supervised approach to fraudulent transaction identification Unsupervised approach to fraudulent transaction identification Summary Chapter 9: Building a Data-Driven Graph-Powered Application Technical requirements Overview of Lambda architectures Lambda architectures for graph-powered applications Graph processing engines Graph querying layer Selecting between Neo4j and GraphX Summary Chapter 10: Novel Trends on Graphs Technical requirements  Learning about 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 Recommendation systems Summary Why subscribe? About PACKT Other Books You May Enjoy Index