1 Discovering Graph Neural Networks

 

This chapter covers:

  • Defining Graphs and Graph Neural Networks (GNNs)
  • Understanding why people are excited about GNNs
  • Recognizing GNN Use Cases
  • A big picture look at solving a problem with a GNN

Sire, there is no royal road to geometry.

Euclid

For data practitioners, the fields of machine learning and data science initially excite us because of the potential to draw non-intuitive and useful insights from data. In particular, the insights from machine learning and deep learning promise to enhance our understanding of the world. For the working engineer, these tools promise to deliver business value in unprecedented ways.

Experience detracts from this ideal. Real data is messy, dirty, biased. Statistical methods and learning systems have limitations. An essential part of the practitioner’s job involves understanding these limitations, and bridging the gap between the ideal and reality to obtain the best solution to a problem.

1.1   What are Graphs & Graph Neural Networks?

 
 
 

1.2   Goals of the book

 
 
 

1.3   Why are people excited about GNNs?

 
 
 

1.4   How do GNNs Work?

 
 

1.5   When to use a GNN?

 

1.5.1   Data modeled as a graph

 
 

1.5.2   A prediction task is involved

 

1.5.3   Incorporation of Node and Edge Features

 
 

1.6   The GNN Workflow

 

1.6.1   Hospital Case: Health Event Prediction

 

1.6.2   Problem Overview

 
 

1.6.3   System and Project Planning

 

1.6.4   Log Data and its Graph Representation

 
 
 

1.6.5   Defining the Machine Learning Problem

 
 
 

1.6.6   System Specification

 
 

1.7   Summary

 
 
 

1.8   References and Further Reading

 
 
 

1.8.1   Academic Overviews of GNNs

 
 
 

1.8.2   References to Section 1.2 Examples

 
 

1.8.3   Academic Overviews of Graphs

 
sitemap

Unable to load book!

The book could not be loaded.

(try again in a couple of minutes)

manning.com homepage
test yourself with a liveTest