skills.rest
jaaaackieLai
jaaaackieLaiCOMMUNITY
Explore all skills by this author →
GitHub

torch-geometric

Design, train, and benchmark Graph Neural Networks with PyTorch Geometric.

Updated Feb 3, 2026
Search Tags:#pytorch#gnn#torch-geometric#node-classification#graph-classification#dataset-loading
One-click install
npx skills add https://github.com/jaaaackieLai/deep-learning-claude-code --skill torch-geometric-jaaaackielai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: torch-geometric
Source: https://github.com/jaaaackieLai/deep-learning-claude-code/tree/main/skills/python-skills/torch-geometric
Command: npx skills add https://github.com/jaaaackieLai/deep-learning-claude-code --skill torch-geometric-jaaaackielai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires torch, torch-geometric, numpy, matplotlib, networkx, and includes scripts (resource) and references (resource) components.

What problem does it solve?

PyTorch Geometric simplifies building and evaluating Graph Neural Networks across domains, from social networks to molecular graphs, reducing setup friction and experimentation time.

Core Features & Use Cases

  • Extensive GNN layers (GCNConv, GATConv, GraphSAGE, GINConv)
  • End-to-end workflows for node classification and graph classification
  • Ready-to-use datasets (Planetoid, TUDataset) and training templates

Quick Start

Load a Planetoid dataset (e.g., Cora), build a simple GCN, and train it for a few epochs to obtain a baseline accuracy.

Frequently Asked Questions about torch-geometric

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a Graph Neural Network for node classification using PyTorch?▼

To build a Graph Neural Network for node classification, use PyTorch Geometric layers like GCNConv to load Planetoid datasets and train models end-to-end. This Skill provides templates to design, train, and benchmark GNNs specifically for node-level tasks.

What's the best way to train a GNN for graph classification on molecular structures?▼

Training a GNN for graph classification involves using layers like GINConv with TUDataset to process molecular structures. This Skill offers ready-to-use datasets and training templates to benchmark graph-level tasks efficiently across molecular domains.

Can I use PyTorch Geometric with NetworkX for visualizing graph datasets?▼

Yes, PyTorch Geometric works with NetworkX for visualizing graph datasets. This Skill includes NetworkX and matplotlib as dependencies, enabling you to render and inspect graph data structures alongside training workflows.

Do I need to install PyTorch before using PyG layers like GraphSAGE?▼

You need to install PyTorch before using PyG layers like GraphSAGE. This Skill requires both PyTorch and the torch-geometric libraries as core dependencies to execute training workflows and handle graph data structures.

Which GNN layers should I choose for link prediction tasks?▼

For link prediction tasks, GNN layers such as GATConv and GraphSAGE are effective choices. This Skill covers these architectures alongside core data structures, providing practical templates to accelerate link prediction experimentation.

Related Skills

Explore More Data & Analytics Skills→
tondevreltondevrel
19

pytorch

Develop and train deep learning models using PyTorch with tensor operations and automatic differentiation.

Community
Advanced
ActiveInferenceInstituteActiveInferenceInstitute
30

gnn-audio-generation

Convert GNN model markdown descriptions into WAV audio representations.

Community
Advanced
jasrajtulsijasrajtulsi

torch-geometric

Builds PyTorch Geometric workflows for node, link, and graph tasks with sampling and explainability.

Community
Advanced
jaechang-hitsjaechang-hits
298

torchdrug

Train GNN models for molecular property prediction using PyTorch and TorchDrug.

Community
Advanced