Introduction to Graph Neural Networks: A Starting Point for Machine Learning Engineers
It serves as an introductory resource for machine learning engineers to understand GNNs, but it is incremental as a survey without new methods or results.
This survey introduces graph neural networks (GNNs) through an encoder-decoder framework, illustrating their behavior with theory and experiments on homogeneous graphs for various training sizes and graph complexities.
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.