How to do Deep Learning on Graphs with Graph Convolutional Networks

Machine learning on graphs is a difficult task due to the highly complex, but also informative graph structure. This post is the first in a series on how to do deep learning on graphs with Graph Convolutional Networks (GCNs), a powerful type of neural network designed to work directly on graphs and leverage their structural information. In this post, I will give an introduction to GCNs and illustrate how information is propagated through the hidden layers of a GCN using coding examples. We'll see how the GCN aggregates information from the previous layers and how this mechanism produces useful feature representations of nodes in graphs. GCNs are a very powerful neural network architecture for machine learning on graphs.