Graph neural network

A graph neural network (GNN) is a class of neural networks for processing data represented by graph data structures. They were popularized by their use in supervised learning on properties of various molecules. Since their inception, several variants of the simple message passing neural network (MPNN) framework have been proposed. These models optimize GNNs for use on larger graphs and apply them to domains such as social networks, citation networks, and online communities. It has been mathematically proven that GNNs are a weak form of the Weisfeiler–Lehman graph isomorphism test, so any GNN model is at least as powerful as this test. There is now growing interest in uniting GNNs with other so-called "geometric deep learning models" to better understand how and why these models work.