What is graph neural network?

Graph Neural Networks (GNNs) are a class of neural networks designed to perform inference on graph-structured data. Unlike traditional neural networks that operate on grid-like data (e.g., images, sequences), GNNs can directly process graphs, which are composed of nodes (vertices) and edges. They learn node representations by aggregating information from their neighbors in the graph. Common uses include node classification, link prediction, and graph classification in domains like social networks, molecular biology, and recommendation systems.