lib-torch-geometric - Develop Graph Neural Networks with PyG
Develop and train graph neural networks with PyTorch Geometric for graph learning, geometric data, heterogeneous graphs, and molecular property prediction.
Tags
Updated: 2026-10-07Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Classify nodes and graphs
- Predict links
- Build GCN models
- Build GAT models
- Build GraphSAGE models
- Process heterogeneous graphs
- Train large-scale graph models
Inputs
- Graph node features
- Graph edge connectivity
- Edge features
- Target labels
- Graph datasets
- Molecular structures
- Task specifications
Outputs
- Graph data objects
- Trained GNN models
- Node classifications
- Graph classifications
- Link predictions
- Molecular property predictions
Requirements
- Python environment
- PyTorch installation
- PyTorch Geometric installation