You are on page 1of 1

1/5/24, 12:02 PM Best Graph Neural Network architectures: GCN, GAT, MPNN and more | AI Summer

important papers on the field. The diagram has been borrowed


from a recent review paper on GNNs by Zhou J. et al1.

Source: Graph Neural Networks: A Review of Methods and Applications1

Before we dive into the different types of architectures, let’s


start with a few basic principles and some notation.

Graph basic principles and notation

Graphs consist of a set of nodes and a set of edges. Both


nodes and edges can have a set of features. From now on, a
node’s feature vector will be denoted as hi ​, where i is the
node’s index. Similarly an edge’s feature vector will be denoted
as eij ,​ where i, j are the nodes that the edge is attached to.

As you might also know, graphs can be directed, undirected,


weighted and weighted. Thus each architecture may be applied
only to a type of graph or to all of them.

So can we start developing a Graph Neural Network?

https://theaisummer.com/gnn-architectures/ 2/18

You might also like