Many important real-world datasets come in the form of graphs or networks: social networks, citation networks, protein-interaction networks, the World Wide Web, etc. The high interpretability of graph and the rise of deep learning has motivated to create a new intersection between deep learning and graph theory. When both these fields basically meet they create what we call geometric deep learning or graph neural network.
It has demonstrated ground-breaking performance on many tasks that require a model to learn from graph inputs. This post will cover the basics of Graph Convolutional Network (GCN) and provide an intuitive explanation how it works together with some coding examples.
The code is implemented for the blog post in https://ospinaforerolab.home.blog/2021/02/27/introduction-to-graph-convolutional-network/