torch-geometric

Build and train Graph Neural Networks with PyTorch Geometric.

3|Updated Apr 17, 2026

Search Tags:#GNN #graph neural networks #node classification #graph classification #link prediction #PyTorch Geometric

Ready to run

npx skills add https://github.com/RamanEbrahimi/raman-marketplace --skill torch-geometric-ramanebrahimi

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: torch-geometric
Source: https://github.com/RamanEbrahimi/raman-marketplace/tree/main/plugins/agentic-research/skills/scientific-skills/torch-geometric
Command: npx skills add https://github.com/RamanEbrahimi/raman-marketplace --skill torch-geometric-ramanebrahimi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires torch, torch_geometric, pyg-lib, torch-scatter, torch-sparse, torch-cluster, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill simplifies the construction and training of Graph Neural Networks (GNNs) with PyTorch Geometric (PyG), providing tools for various graph-related tasks.

Core Features & Use Cases

Graph Data Structures: Offers Data and HeteroData for graph representation.
GNN Layers: Integrates 60+ GNN layer implementations for diverse tasks like node classification and graph classification.
Mini-batch Training: Supports scalable mini-batch training for large graphs.
Heterogeneous Graphs: Facilitates working with graphs with multiple node and edge types.
Use Case: If you need to build a GNN for a graph-based task like node classification or link prediction, this Skill is invaluable.

Quick Start

Execute the torch-geometric skill with the command: 'uv add torch_geometric'.

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?▼

You can build a Graph Neural Network for node classification using PyTorch Geometric by representing graph data with the Data object and constructing models with its 60+ integrated GNN layer implementations tailored for node classification tasks.

Can I train Graph Neural Networks on large graphs using mini-batches?▼

Yes, you can train Graph Neural Networks on large graphs using mini-batches. PyTorch Geometric supports scalable mini-batch training, allowing you to process large graph structures efficiently without loading the entire graph into memory simultaneously.

What is the best way to handle heterogeneous graphs with multiple node and edge types?▼

The best way to handle heterogeneous graphs with multiple node and edge types is using the HeteroData object in PyTorch Geometric. It facilitates working with complex graph structures containing multiple node and edge types for diverse machine learning applications.

Do I need additional libraries besides PyTorch to use PyTorch Geometric for link prediction?▼

Yes, you need additional libraries besides PyTorch to use PyTorch Geometric for link prediction. You must install pyg-lib, torch-scatter, torch-sparse, and torch-cluster to support specific graph operations required for link prediction and other GNN tasks.

Does PyTorch Geometric support graph classification tasks?▼

Yes, PyTorch Geometric supports graph classification tasks. It provides a comprehensive library with 60+ GNN layer implementations that can be applied to graph classification, enabling you to predict properties of entire graph structures.