Overview of Graph Neural Networks

Graph neural network (GNN) is a special kind of network, which works with a graph as a data sample. The typical neural network works with arrays, while GNN works with graphs.

Now before we dive into the technicalities of GNN, let us (re)visit graphs.

Graphs are nothing but the connection of various nodes (vertices) via edges. The nodes, as well as edges, have their values depending on the data.

Mathematically graphs are represented as a function of vertices and edges like follows:

G = Ω (V,E)

T...