None
EN
A Gentle Introduction to Graph Neural Networks
['Sanchez-Lengeling', 'Reif', 'Pearce', 'Wiltschko', 'Alexander B.', 'Author Contributions']
Distill
We’re going to build GNNs using the “message passing neural network” framework proposed by Gilmer et al. using the Graph Nets architecture schematics introduced by Battaglia et al. GNNs adopt a “graph-in, graph-out” architecture meaning that these model types accept a graph as input, with information loaded into its nodes, edges and global-context, and progressively transform these embeddings, without changing the connectivity of the input graph. By stacking message passing GNN layers together, a node can eventually incorporate information from across the entire graph: after three layers, a node has information about the nodes three steps away from it.