You are on page 1of 1

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

Best Graph Neural Network


architectures: GCN, GAT, MPNN and
more
Sergios Karagiannakos on 2021-09-23 · 11 mins

Graph Neural Networks

Traditionally, datasets in Deep Learning applications such as


computer vision and NLP are typically represented in the
euclidean space. Recently though there is an increasing
number of non-euclidean data that are represented as graphs.

To this end, Graph Neural Networks (GNNs) are an effort to


apply deep learning techniques in graphs. The term GNN is
typically referred to a variety of different algorithms and not a
single architecture. As we will see, a plethora of different
architectures have been developed over the years. To give you
an early preview, here is a diagram presenting the most

https://theaisummer.com/gnn-architectures/ 1/18

You might also like