Graph-Powered Machine Learning

by Alessandro Nego

Overview

Upgrade your machine learning models with graph-based algorithms, the perfect structure for complex and interlinked data.

Summary
In Graph-Powered Machine Learning, you will learn:

The lifecycle of a machine learning project
Graphs in big data platforms
Data source modeling using graphs
Graph-based natural language processing, recommendations, and fraud detection techniques
Graph algorithms
Working with Neo4J

Graph-Powered Machine Learning teaches to use graph-based algorithms and data organization strategies to develop superior machine learning applications. You’ll dive into the role of graphs in machine learning and big data platforms, and take an in-depth look at data source modeling, algorithm design, recommendations, and fraud detection. Explore end-to-end projects that illustrate architectures and help you optimize with best design practices. Author Alessandro Negro’s extensive experience shines through in every chapter, as you learn from examples and concrete scenarios based on his work with real clients!

Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.

About the technology
Identifying relationships is the foundation of machine learning. By recognizing and analyzing the connections in your data, graph-centric algorithms like K-nearest neighbor or PageRank radically improve the effectiveness of ML applications. Graph-based machine learning techniques offer a powerful new perspective for machine learning in social networking, fraud detection, natural language processing, and recommendation systems.

About the book
Graph-Powered Machine Learning teaches you how to exploit the natural relationships in structured and unstructured datasets using graph-oriented machine learning algorithms and tools. In this authoritative book, you’ll master the architectures and design practices of graphs, and avoid common pitfalls. Author Alessandro Negro explores examples from real-world applications that connect GraphML concepts to real world tasks.

What's inside

Graphs in big data platforms
Recommendations, natural language processing, fraud detection
Graph algorithms
Working with the Neo4J graph database

About the reader
For readers comfortable with machine learning basics.

About the author
Alessandro Negro is Chief Scientist at GraphAware. He has been a speaker at many conferences, and holds a PhD in Computer Science.

Table of Contents
PART 1 INTRODUCTION
1 Machine learning and graphs: An introduction
2 Graph data engineering
3 Graphs in machine learning applications
PART 2 RECOMMENDATIONS
4 Content-based recommendations
5 Collaborative filtering
6 Session-based recommendations
7 Context-aware and hybrid recommendations
PART 3 FIGHTING FRAUD
8 Basic approaches to graph-powered fraud detection
9 Proximity-based algorithms
10 Social network analysis against fraud
PART 4 TAMING TEXT WITH GRAPHS
11 Graph-based natural language processing
12 Knowledge graphs

Product Details

ISBN-13:	9781617295645
Publisher:	Manning
Publication date:	09/28/2021
Pages:	496
Product dimensions:	7.38(w) x 9.25(h) x 0.60(d)

About the Author

Alessandro Negro is a Chief Scientist at GraphAware. With extensive experience in software development, software architecture, and data management, he has been a speaker at many conferences, such as Java One, Oracle Open World, and Graph Connect. He holds a Ph.D. in Computer Science and has authored several publications on graph-based machine learning.

Table of Contents

Foreword xiii

Preface xv

Acknowledgments xvii

About this book xix

About the author xxiii

About the cover illustration xxiv

Part 1 Introduction 1

1 Machine learning and graphs: An introduction 3

1.1 Machine learning project life cycle 5

Business understanding 7

Data understanding 8

Data preparation 8

Modeling 9

Evaluation 9

Deployment 9

1.2 Machine learning challenges 10

The source of truth 10

Performance 13

Storing the model 14

Real time 14

1.3 Graphs 15

What is a graph 15

Graphs as models of networks 17

1.4 The role of graphs in machine learning 23

Data management 25

Data analysis 25

Data visualization 26

1.5 Book mental model 27

2 Graph data engineering 30

2.1 Working with big data 33

Volume 34

Velocity 36

Variety 38

Veracity 39

2.2 Graphs in the big data platform 40

Graphs are valuable for big data 41

Graphs are valuable for master data management 48

2.3 Graph databases 53

Graph database management 54

Sharding 57

Replication 60

Native vs. non-native graph databases 61

Label property graphs 67

Graphs in machine learning applications 71

3.1 Graphs in the machine learning workflow 73

3.2 Managing data sources 76

Monitor a subject 79

Detect a fraud 82

Identify risks in a supply chain 85

Recommend items 87

3.3 Algorithms 93

Identify risks in a supply chain 93

Find keywords in a document 96

Monitor a subject 98

3.4 Storing and accessing machine learning models 100

Recommend items 101

Monitoring a subject 103

3.5 Visualization 106

3.6 Leftover: Deep learning and graph neural networks 109

Part 2 Recommendations 113

4 Content-based recommendations 119

4.1 Representing item features 122

4.2 User modeling 136

4.3 Providing recommendations 143

4.4 Advantages of the graph approach 164

5 Collaborative filtering 166

5.1 Collaborative filtering recommendations 170

5.2 Creating the bipartite graph for the User-Item dataset 172

5.3 Computing the nearest neighbor network 177

5.4 Providing recommendations 189

5.5 Dealing with the cold-start problem 194

5.6 Advantages of the graph approach 198

6 Session-based recommendations 202

6.1 The session-based approach 203

6.2 The events chain and the session graph 206

6.3 Providing recommendations 212

Item-based k-NN 213

Session-based k-NN 219

6.4 Advantages of the graph approach 224

7 Context-aware and hybrid recommendations 227

7.1 The context-based approach 228

Representing contextual information 231

Providing recommendations 235

Advantages of the graph approach 253

7.2 Hybrid recommendation engines 254

Multiple models, single graph 256

Providing recommendations 258

Advantages of the graph approach 260

Part 3 Fighting Fraud 263

8 Basic approaches to graph-powered fraud detection 265

8.1 Fraud prevention and detection 267

8.2 The role of graphs in fighting fraud 271

8.3 Warm-up: Basic approaches 279

Finding the origin point of credit card fraud 279

Identifying a fraud ring 287

Advantages of the graph approach 293

Proximity-based algorithms 295

9.1 Proximity-based algorithms: An introduction 296

9.2 Distance-based approach 298

Storing transactions as a graph 300

Creating the k-nearest neighbors graph 302

Identifying fraudulent transactions 309

Advantages of the graph approach 318

Social network analysis against fraud 320

10.1 Social network analysis concepts 323

10.2 Score-based methods 326

Neighborhood metrics 330

Centrality metrics 336

Collective inference algorithms 344

10.3 Cluster-based methods 348

10.4 Advantages of graphs 354

Part 4 Taming text with graphs 357

11 Graph-based natural language processing 359

11.1 A basic approach: Store and access sequence of words 363

Advantages of the graph approach 373

11.2 NLP and graphs 373

Advantages of the graph approach 387

12 Knowledge graphs 389

12.1 Knowledge graphs: Introduction 390

12.2 Knowledge graph building: Entities 393

12.3 Knowledge graph building: Relationships 402

12.4 Semantic networks 409

12.5 Unsupervised keyword extraction 415

Keyword co-occurrence graph 423

Clustering keywords and topic identification 425

12.6 Advantages of the graph approach 428

Appendix A Machine learning algorithms taxonomy 431

Appendix B Neo4j 435

Appendix C Graphs for processing patterns and workflows 449

Appendix D Representing graphs 458

Index 461