Skip to main content

​
torch-geometric

PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.
Category: data-science-and-ml · License: MIT · Version: 1.2

​
Install

​
When to use it

PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.

​
Full playbook

Read SKILL.md for the complete workflow, references and any scripts. The agent installer copies the full skill folder.