Introduction to Graph Neural Networks: A Starting Point for Machine Learning Engineers

TL;DR

This paper introduces graph neural networks, explaining their structure, applications, and behavior through experiments, serving as a foundational resource for machine learning engineers interested in graph-based models.

Contribution

It provides a comprehensive introduction to graph neural networks, including theoretical insights and practical examples across various graph analytic tasks.

Findings

GNNs perform well on diverse graph tasks

Behavior varies with training size and graph complexity

Experiments illustrate GNN capabilities and limitations

Abstract

Graph neural networks are deep neural networks designed for graphs with attributes attached to nodes or edges. The number of research papers in the literature concerning these models is growing rapidly due to their impressive performance on a broad range of tasks. This survey introduces graph neural networks through the encoder-decoder framework and provides examples of decoders for a range of graph analytic tasks. It uses theory and numerous experiments on homogeneous graphs to illustrate the behavior of graph neural networks for different training sizes and degrees of graph complexity.