Variants of Graph Neural Networks (GNN)

Graphs are data structures consisting of nodes and the relationships between nodes, known as edges. Recently there have been many model architectures leveraging the power of graphs and their characteristics. The fundamental models were called Graph Neural Networks. Once the potential was discovered of these graph-based models, the artificial intelligence community has continuously developed the variants of graph-based models depending on various use cases.

Just as a refresher, let us look at th...