Complete Guide to Graph Representation Learning with Case Studies

AvE. Chandra Blessie,Pethuru Raj Chelliah

Inbunden, Engelska, 2026

1 690 kr

Kommande

Beskrivning

Comprehensive resource on graph representation learning (GRL), exploring fundamental principles, advanced methodologies, and case studies A Complete Guide to Graph Representation Learning with Case Studies provides a concise understanding of the subject of graph representation learning (GRL), a rapidly advancing field in the domain of machine learning. The book explores basic concepts to state-of-the-art techniques, enabling readers to progress from a fundamental understanding of the approach to mastering its application. The authors also cover the topics of graph embedding methods, graph neural network (GNN) -based approaches, and the latest trends in GRL such as deep learning, transfer learning, graph pooling, alignment, and matching, and graph machine learning. The book includes examples of applications of graph learning methods with real-world case studies in which the covered methods can be utilized. It also includes innovative solutions to graph machine learning problems such as node classification, link prediction, and unsupervised learning, and discusses neighborhood overlap visualization techniques and overlapping neighborhoods in heterogeneous graphs. Finally, the book provides an overview of open and ongoing research directions and student projects, providing a glimpse into potential avenues for future work. The book also includes information on: Node-level features such as node degree, node centrality, closeness, betweenness, eigenvector, page rank centrality, clustering coefficient, closed triangles, egograph, and motifsNeighborhood sampling techniques such as breadth-first sampling, depth-first sampling, snowball sampling, random walk, shallow walk, edge sampling, link-based sampling, and metapath-based samplingDeep learning models including Graph Autoencoder (GAE), Variational Graph Encoder (VGAE), and Graph Attention Network (GAN)Graph alignment and matching, covering subgraph matching and embedding for matchingA Complete Guide to Graph Representation Learning with Case Studies is a thorough and up-to-date reference on the subject for engineers and researchers in data science and machine learning as well as graduate students in related programs of study.

Produktinformation

Utgivningsdatum:2026-09-28
Format:Inbunden
Språk:Engelska
Antal sidor:464
Förlag:John Wiley & Sons Inc
ISBN:9781394314843

Utforska kategorier

Systemvetenskap och AI inom Data och IT

Mer om författaren

E. Chandra Blessie, PhD, is Dean of Innovation, School of Innovation, KG College of Arts and Science, Coimbatore, Tamil Nadu, India.Pethuru Raj Chelliah, PhD, SMIEEE, is the Principal AI Architect at Infocion Inc., AKR Tech Park, Hosur Road, Bangalore, India.B. Sundaravadivazhagan, PhD, is a Professor with the College of Computing and Information Sciences at the University of Technology and Applied Sciences Al Mussanah, Oman.

Innehållsförteckning

PART I : FOUNDATION LEARNING CHAPTER 1 : INTRODUCTION TO GRAPH AND GRAPH REPRESENTATION LEARNING (GRL)1. Introduction1.1 What is a Graph?1.2 Importance of Graph1.3 Types of Graph1.3.1 Directed Graph1.3.2 Undirected Graph1.3.3 Weighted Graph1.3.4 Multigraph1.3.5 Complete Graph1.3.6 Planar and Bipartite Graph1.3.7 Hypergraph1.3.8 Hierarchical Graphs1.3.9 Homogeneous and Heterogeneous Graphs1.4 Overview of Graph Representation Learning1.4.1 Benefits of Graph Representation Learning (GRL)1.5 Overview of Graph Connectivity1.5.1 Its Definition1.5.2. Importance of Graph Connectivity1.5.3. Role of Graph Connectivity1.6 Foundation on Graph Neighborhood1.6.1 Introduction1.6.2 Properties of Graph Neighborhoods1.6.3 Types of Node/Graph Neighborhoods1.6.3.1 Direct/Local Neighborhood (1-Hop Neighborhood)1.6.3.2 K-Hop Neighborhood1.6.3.3 Ego Neighborhood1.6.3.4 Attention-based neighborhoods1.6.3.5 Structural Neighborhood (Graphlets and Motifs)1.6.3.6 Graphlets1.7 Applications of Graph1.7.1 Traffic Prediction in Transportation1.7.2 Pattern recognition1.7.3 Social Network Analysis1.7.4 Application of Graphs in Biology1.7.5 Application of graphs in chemistry1.8 Case studies of Graph Representation Learning (GRL)1.8.1 Case study in Social Network Analysis1.8.2 Case Study in Fraud Detection for Financial Transactions1.8.3 Case Study in Molecular Biology1.9 ConclusionReferencesCHAPTER 2 : FUNDAMENTAL CONCEPTS OF GRAPH STRUCTURES2.1 Introduction to Graph Structures2.1.1 Characteristics of Graph Structure2.2 Node-Level features2.2.1 Node Degree2.2.2 Node Centrality Measures2.3 Structural-Level features2.3.1 Clustering Coefficient measure2.3.2 Closed Triangles2.3.3 Egographs2.3.4 Motifs2.4 Graph-Level Features2.4.1 Structural Properties of Graphs2.4.1.1 Graph Degree and Density2.4.1.2 Graph Eccentricity and Modularity2.5 Graph-Based Representation Techniques2.5.1 Graph Clustering Coefficient2.5.2 Bag of Nodes (BoN)2.5.3 Weifeiler-Lehman Kernel2.5.4 Graphlets and Path-Based Methods2.6 Graph Representation Matrix2.6.1 Types of Graph Representation Matrices2.6.1.1 Adjacency Matrix2.6.1.2 Incidence Matrix2.6.1.3 Laplacian Matrix2.6.1.4 Transition Matrix2.7 ConclusionReferencesCHAPTER 3 OVERLAPPING NEIGHBORHOOD IN GRAPH 3.1 Definition and its importance3.2 Methods for Detecting Neighborhood overlap3.2.1 Local Overlap Measures3.2.1.1 Jaccard Similarity measure3.2.1.2 Adamic-Adar Index3.2.1.3 Resource Allocation Index3.2.1.4 Global Overlap Measures3.2.1.5 Katz Index3.2.1.6 SimRank3.2.1.7 PageRank-Based Similarity3.3 Neighborhood Overlap Visualization Techniques3.3.1 Venn Diagram3.3.2 Node-Link Diagrams (Graph Representation)3.3.3 Heatmaps3.3.4 Edge Bundling3.3.5 Graph Embedding & Projection (t-SNE, UMAP)3.3.6 Ego Networks (Subgraph Extraction )3.4 Overlapping Neighborhoods in Heterogeneous Graphs3.4.1 Introduction3.4.2 Methods for Detecting Overlapping Neighborhoods in Heterogeneous GraphsA. Meta-Path Based ApproachesB. Clustering-based methods3.5 Case Studies on neighborhood overlap detection in real-world scenarios3.5.1 Application of Graph Neighborhood in Healthcare3.5.2 Case studies on Social networks: overlapping user communities and friendrecommendations3.6 ConclusionReferencesPART II : CORE GRAPH REPRESENTATION LEARNING CHAPTER 4 : GRAPH MACHINE LEARNING 4.1 Introduction to Graph Machine Learning (GML)4.1.1 Key features of GML4.1.2 GML Vs traditional ML4.2 Types of Tasks in GML4.2.1 Supervised Graph Machine Learning (GML) tasks4.2.1.1 Node Classification4.2.1.2 Link Prediction4.2.1.3 Edge Classification4.2.1.4 Graph / Subgraph classification4.2.2 Unsupervised Graph Machine Leaning tasks4.2.2.1 Introduction4.2.2.2 Node ClusteringA. Spectral ClusteringB. Label Propagation Algorithm (LPA)C. Louvain Method for Community Detection4.2.3 Case studies and Applications of GMLCase study 1 : GML in Disease predictionCase study 2 : Drug Discovery and Development4.3 ConclusionReferencesCHAPTER 5 : GRAPH SAMPLING 5.1 Introduction5.1.1 Issues related to large and complex graphs5.1.2 Definition with examples5.1.3 Challenges of using sampling5.2 Types of Graph Sampling5.2.1 Node Sampling5.2.1.1 Overview of Node Sampling5.2.1.2 Types of Node SamplingA. Uniform Node SamplingB. Degree-based Node SamplingC. Stratified Node SamplingD. Snowball Node SamplingE. Random Walk-based Sampling5.2.2 Edge Sampling5.2.2.1 Overview of Edge Sampling5.2.2.2 Types of Edge SamplingA. Uniform Edge SamplingB. Weighted Edge SamplingC. Temporal Edge Sampling5.2.3 Neighborhood Sampling5.2.3.1 Overview of Neighborhood Sampling5.2.3.2 Types of Neighborhood SamplingA. K-Hop Neighborhood SamplingB. Random Walk Neighborhood SamplingC. Layer-wise Neighborhood Sampling5.2.4 Subgraph sampling5.3 Case Studies5.3.1 Case Study: Sampling Patient Networks for Disease Prediction5.3.2 Case Study: Sampling in Learning Management System (LMS)5.3.3 Case Study: Community-Based Sampling for Efficient Social Network Analysis5.4 ConclusionReferencesCHAPTER 6 : GRAPH POOLING 6.1 Introduction to Graph Pooling6.1.1 What is Graph Pooling?6.1.2 Why is Graph Pooling Important?6.2 Types of Graph Pooling6.2.1 Flat Pooling6.2.1.1Methods of flat PoolingA. Sum PoolingB. Mean PoolingC. Max PoolingD. Attention Pooling6.2.1.2 Applications of Flat Pooling in Graph-Level Tasks6.2.2. Hierarchical Pooling6.2.2.1 Types of Hierarchical Pooling6.2.2.2Common techniquesA. Top-K PoolingB. DiffPool (Differentiable Pooling)C. SAGPool (Self-Attention Graph Pooling)D. MinCutPool (Minimum Cut Pooling)6.2.3 Comparison between Flat pooling and Hierarchical pooling6.3 Case Study on Graph Pooling6.4 ConclusionReferencesCHAPTER 7 : GRAPH NEURAL NETWORKS AND DEEP REPRESENTATION LEARNING7.1 Foundation of Deep Representation Learning on graphs7.1.1 Basic concept7.1.2 Challenges and importance of Deep Learning on Graphs7.1.3 Approach of Deep Learning on Graph7.1.4 Characteristics and Benefits of Deep Learning on Graph 7.2 Introduction to Graph Neural Networks (GNNs)7.2.1 GNN Architecture Overview7.2.2 Message Passing in GNNs7.2.3 Case Study on Graph Neural Network (GNNs)7.2.3.1 Case Study 1: Enhancing Credit Card Fraud Detection with CaT-GNN7.2.3.2 Case Study: GNNs for Drug-Drug Interaction (DDI) Prediction inHealthcare7.3 Fundamentals of Graph Convolution Networks (GCNs)7.3.1 Core concepts and motivation for GCNs7.3.2 Workflow process of Graph Convolution Network (GCN)7.4 Types of Graph Neural Networks7.4.1 Graph Recurrent Neural Networks (GRNN)7.4.1.1 Definition with illustration7.4.1.2 Working process of GRNN7.4.1.3 GRNN Architecture7.4.1.4 Applications of GRNN7.4.2 Graph Attention Networks (GAT)7.4.2.1 Definition with illustration7.4.2.2 Working Process of Graph Attention Networks (GAT)7.4.2.3 Architecture of GAT7.4.2.4 Application of GAT7.5 Applications of Deep Learning on Graph7.6 ConclusionReferencesCHAPTER 8 : ADVANCED GRAPH NEURAL NETWORKS 8.1 Spatial-Temporal Graph Neural Networks (ST-GNNs)8.1.1 Definition with illustration8.1.2 Working Process of Spatial-Temporal Graph Neural Networks (ST-GNN)8.1.3 Architecture of ST-GNNs8.1.4 Application of ST-GNNs8.2 Dynamic Graph Neural Networks8.2.1 Work Process of Dynamic GNNs8.2.2 Example: Dynamic Graph – Social Interaction8.2.3 Dynamic Graph Neural Network modelsA. Temporal Graph Attention Network (TGAT)B. Dynamic Graph Convolutional Network (DyGCN)8.3 Hypergraph Neural Networks8.3.1 Architecture of HGNN8.3.2 Working Process of HGNN8.4 Unsupervised Deep Learning Models8.4.1 Graph Autoencoder (GAE)8.4.1.1 GAE – Workflow with its Architecture8.4.1.2 GAE Algorithm8.4.1.3 Applications of GAE8.4.1.4 Advantages and Limitations of GAE8.4.2 Variational Auto Encoder (VAE)8.4.2.1 VGAE – Workflow with its Architecture8.4.2.2 Algorithm: Variational Graph Autoencoder (VGAE)8.4.2.3 Advantages and Limitations of VGAE8.5 ConclusionReferencesPART III : ADVANCED ANALYSIS AND TECHNIQUES CHAPTER 9 : GRAPH ALIGNMENT AND MATCHING9.1 Introduction to Graph Alignment and Matching9.2 Definition and purpose of graph alignment and matching.9.3 Example for Graph Matching and Alignment9.4. Types of Graph Alignment and Matching9.4.1. Exact Graph Matching (Graph Isomorphism)9.4.2. Inexact/Fuzzy Matching9.4.3. Global Alignment9.4.4. Local Alignment9.5. Mathematical Approaches for Graph Alignment and Matching9.5.1. Graph Embedding + Distance Minimization9.5.2 Gromov-Wasserstein distance9.5.3 Contrastive Learning for Graph Matching9.5.4 Deep Graph Matching Networks (e.g., DGMC)9.6. Case Studies on Graph Alignment and Matching9.6.1 Graph Alignment and Matching in Healthcare9.6.2. Matching Users Across Facebook and Twitter Accounts in Social Networks9.7 ConclusionReferencesCHAPTER 10 : NEIGHBORHOOD RECONSTRUCTION METHODS10.1 Introduction10.1.1 Introduction to Neighborhood Reconstruction in Graphs10.1.2 Benefits of Neighborhood Reconstruction in Graphs10.1.3 Importance of reconstructing graph structures10.2 Neighborhood Reconstructions Techniques10.2.1 Matrix Factorization10.2.2 Embedding Models10.2.3 Similarity Measures10.3 Neighborhood reconstruction methods10.3.1 An Encoder-Decoder method10.4. Applications of Encoder-Decoder in Graph Learning10.5 Case Study on Neighborhood reconstruction10.5.1Case Study on Urban Road Network Reconstruction Using Neighborhood Inference10.6 ConclusionReferencesCHAPTER 11 : TRANSFER LEARNING ON GRAPH11.1 Introduction11.2 Overview of Transfer graph learning11.2.1 Key features of TGL11.2.2 Benefits of Transfer Graph Learning11.2.3 The need of TGL and its necessity11.2.4 TGL Vs GL11.3 Types of transfer learning (TGL)11.3.1 Inductive Transfer Graph Learning (ITGL)11.3.1.1 Working Process of Inductive Transfer Graph Learning11.3.1.2 Algorithm : GraphSAGE (Graph Sample and Aggregate)11.3.1.3 Key Features and Benefits of GraphSAGE11.3.2 Transductive Transfer Graph Learning (TTGL)11.3.2.1 Working Process of Transductive Transfer Graph Learning11.3.2.2 Algorithm : GCN-DA (Graph Convolutional Network with Domain Adaptation)11.3.2.3 Key Features and Benefits of GCN-DA11.3.3 Heterogeneous Transfer Learning (HTL)11.3.3.1 Working Process of Heterogeneous Transfer Learning11.3.3.2 Algorithm : Heterogeneous Feature Augmentation (HFA)11.3.3.3 Key Features and Benefits of HFA11.4 Key Techniques in Transfer Graph Learning (TGL)11.4.1 Feature-Based Transfer Techniques11.4.1.1 Transfer Component Analysis (TCA)11.4.1.2 Domain Adversarial Neural Networks (DANN)11.4.2 Structure-Based Transfer Techniques11.4.2.1 Overview and its Definition11.4.2.2 Algorithm for Structure-Based Transfer Learning11.4.2.3 Flow process and its diagram11.4.2.4 Meta-Path-Based Learning11.5 Techniques Comparison11.5.1 Inductive vs. Transductive Transfer Graph Learning11.5.2 Feature-based transfer graph learning vs structure-based transfer graph learning11.6 Case studies11.6.1 Case Study: Enhancing Graph Anomaly Detection with Dual-Level Knowledge Distillation11.6.2 Transfer Learning in Biological Networks using Geneformer11.7 ConclusionReferencesPART IV : EMERGING TRENDS WITH CASE STUDIESCHAPTER 12 : GRAPH CONTRASTIVE LEARNING 12.1 Introduction to Self-Supervised Learning12.1.1 Definition with example12.1.2 Key Characteristics of Self-Supervised Learning (SSL)12.1.3 Types of Self-Supervised Tasks12.1.4 Application in Graph Domain12.2 Comparison with Supervised Graph Learning12.3 Fundamentals of Graph Contrastive Learning (GCL)12.3.1 Motivation : Why Contrastive Learning for graphs?12.3.2 Key Components and Mechanism12.4 Graph Contrastive Learning Frameworks12.5 ConclusionReferencesCHAPTER 13 : MULTIMODEL GRAPH REPRESENTATION LEARNING13.1 Introduction to Multimodal GRL13.2 Types of Modalities in Graph data13.2.1 Text Modalities13.2.2 Image Modalities13.2.3 Audio Modalities13.3 Data Fusion Techniques in Multimodal GRL13.3.1 What is Data Fusion?13.3.2Data Fusion Techniques13.4 Applications13.4.1 Autonomous Vehicles13.4.2 Agriculture – Pest Detection Network13.5 ConclusionReferencesCHAPTER 14 : DEMYSTIFYING GRAPHS EMBEDDINGS AND INDUSTRIAL APPLICATIONS14.1 Introduction14.2 The Importance of Graph Representation14.3 Making Sense out of Graph-structured Data14.4 Delineating AI Model Engineering Steps14.5 Graph Embeddings14.5.1 The Need for Graph Embeddings14.5.2 Knowledge Graph Embeddings14.5.3 The Advantages of Graph Embeddings14.5.4 Graph Embedding Applications14.5.5 Types of Graph Embeddings14.6 Edge embedding techniques14. 7 Applications of Graph Embeddings14.8 ConclusionReferencesChapter 15 : KNOWLEDGE GRAPH FOUNDATION, TECHNIQUES WITH ITS CASE STUDIES15.1 Introduction to Knowledge Graph15.1.1 History and evolution15.1.2 Definition and core concepts15.1.3 Difference between KGs and traditional databases15.2 Construction of a Knowledge Graph15.3 Techniques for Building a Knowledge Graph15..3.1 Named Entity Recognition (NER)15.3.2 Entity Linking and Disambiguation15.3.3 Relation Extraction (RE)15.3.4 Ontology Engineering15.4 Representation and Storage15.4.1 Introduction to Representation and Storage of Knowledge Graphs15.4.2 RDF Triples and SPARQL15.5 Case Studies of Knowledge Graph15.5.1 Supply Chain Management using Knowledge Graph15.5.2 DRKG: A Knowledge Graph Approach to Drug Repurposing for COVID-1915.6 ConclusionReferencesChapter 16 : GRAPH REPRESENTATION LEARNING IN WIRELESS COMMUNICATION AND TOURIST MOVEMENT ANALYSIS16.1 A Graph-Theoretic Framework for Analyzing Tourist Flows from Social Media Data16.2 Knowledge-Driven Graph Learning for Next-Generation Wireless Networks16.3 Applications of Graph Representation Learning in Wireless Networks and Urban Tourism16.4 Other areas of GRL applications16.5 ConclusionReferences