GCN

GCN (Graph Convolutional Network) is a foundational graph neural network architecture developed by Thomas Kipf and Max Welling, designed for efficient semi-supervised learning on graph-structured data.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.