torch-geometric-graph-neural-networks

Installation
SKILL.md

PyTorch Geometric (PyG) — Graph Neural Networks

Overview

PyTorch Geometric is a library built on PyTorch for developing and training Graph Neural Networks (GNNs). It provides 40+ convolutional layers, mini-batch processing via block-diagonal adjacency matrices, neighbor sampling for large-scale graphs, and heterogeneous graph support for multi-type node/edge networks.

When to Use

  • Node classification on citation, social, or biological networks
  • Graph-level classification (molecular activity, protein function)
  • Link prediction (knowledge graphs, recommendation systems)
  • Molecular property prediction (drug discovery, quantum chemistry)
  • 3D point cloud processing and mesh analysis
  • Large-scale graph learning with neighbor sampling (>100K nodes)
  • Heterogeneous graphs with multiple node/edge types
  • For non-graph deep learning → use PyTorch directly
  • For traditional graph algorithms (shortest path, centrality) → use NetworkX

Prerequisites

Related skills

More from jaechang-hits/sciagent-skills

Installs
9
GitHub Stars
152
First Seen
Mar 16, 2026