Graph Attention Network: Node Classification

This simulator runs a real Graph Attention Network (GAT) layer over a 24-node graph laid out and rendered in 3D. Each node carries a feature vector drawn from one of three class centers; a directed k-nearest-neighbor graph connects it to its most feature-similar peers. On every parameter change the layer computes LeakyReLU attention scores for each edge, softmax-normalizes them per neighborhood exactly as in the GAT paper, aggregates neighbor features into a new representation, and classifies each node with a linear readout. Click any node to see the raw attention weights it places on its own neighbors and how concentrated (low-entropy) or diffuse (high-entropy) that attention is.