Home▸Machine Learning & Neural Networks▸Graph Attention Networks: Learned Attention Visualizer

Graph Attention Networks: Learned Attention Visualizer

Interactive 3D visualizer for Graph Attention Networks (GAT): watch a node's attention coefficients get computed live via LeakyReLU scoring and softmax normalization across its neighbors, with multi-head attention, entropy and sanity-check readouts.

Machine Learning & Neural Networks3DAdvanced60 FPS📱 Mobile-adapted⇄ 2D version

Graph Neural Networks that use a fixed sum, mean or max to combine neighbor information treat every neighbor as equally important — Graph Attention Networks (GAT) instead learn, per edge, exactly how much weight each neighbor deserves. This simulator computes real GAT attention coefficients on a small 3D graph: pick a query node and watch a live LeakyReLU-scored, softmax-normalized attention distribution light up its incoming edges, switch between independently-learned attention heads, and drag the LeakyReLU slope and softmax sharpness controls to see the distribution sharpen or flatten in real time, backed by a sum-check and entropy readout that confirm the softmax normalization on every recompute.

⚙ Under the hood

Interactive 3D visualizer for Graph Attention Networks: pick a query node and watch its real LeakyReLU-scored, softmax-normalized attention coefficients light up its neighbors, switch between independently-learned attention heads, and see the distribution sharpen or flatten live.

graph neural networksattention mechanismGATsoftmaxdeep learningmessage passing

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install