alterlab-torch-geometric

Community

Build scalable graph neural networks with PyG.

AuthorAlterLab-IEU
Version1.0.0
Installs0

System Documentation

What problem does it solve?

PyTorch Geometric (PyG) provides a comprehensive, production-ready toolkit to design, train, and deploy graph neural networks on real-world graph data, reducing boilerplate and expediting model experimentation.

Core Features & Use Cases

  • Graph neural network primitives (GCNConv, GATConv, GraphSAGE, GIN) for node and graph-level tasks.
  • Data handling and datasets (Data objects, Planetoid, TUDataset, MoleculeNet, OGB) with transforms and loaders.
  • End-to-end workflows including model templates, training loops, evaluation utilities, benchmarking scripts, and templates for rapid experimentation.

Quick Start

Install PyG, load a dataset, define a simple GNN model, and start training.

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: alterlab-torch-geometric
Download link: https://github.com/AlterLab-IEU/AlterLab-Academic-Skills/archive/main.zip#alterlab-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 471,000+ vetted skills library on demand.