Schematic of the algorithm. Chemical abundances define node features, and IoM defines the edges. The GAT autoencoder reconstructs the node features, learning which links to retain or break. Chemically similar stars remain connected, while dissimilar ones disconnect. Top: original (left) vs. reconstructed abundances (right) with two of the five latent-space dimensions in the middle. This diagram was created with draw.io (JGraph 2021).