torch-geometric

Community

Graph neural networks with PyG for graph learning.

AuthorTianyi-Billy-Ma
Version1.0.0
Installs0

System Documentation

What problem does it solve?

PyTorch Geometric (PyG) provides a rich library and tutorials for building, training, and deploying Graph Neural Networks on graphs, heterographs, and point clouds.

Core Features & Use Cases

  • GNN primitives: GCConv, GATConv, GraphSAGE, GIN, TransformerConv, and more
  • Diverse tasks: Node classification, graph classification, link prediction, molecular property prediction
  • Datasets & templates: Built-in datasets and boilerplates for common GNN architectures

Quick Start

Install PyG and run one of the included scripts (e.g., train a simple GCN on Cora using the templates in scripts/). Adapt to your own dataset.

Dependency Matrix

Required Modules

torchtorch-geometricnumpy

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: torch-geometric
Download link: https://github.com/Tianyi-Billy-Ma/PyTemplate/archive/main.zip#torch-geometric

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 430,000+ vetted skills library on demand.