skills.rest
qinyan-ai
qinyan-aiCOMMUNITY
Explore all skills by this author →
GitHub

torch-geometric

Build and benchmark Graph Neural Networks for node classification, link prediction, and heterogeneous graphs.

48|6|Updated Mar 9, 2026
Search Tags:#research#models#pytorch#graph#datasets#pyg#gnn
One-click install
npx skills add https://github.com/qinyan-ai/qinyan-academic-skills --skill torch-geometric-qinyan-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: torch-geometric
Source: https://github.com/qinyan-ai/qinyan-academic-skills/tree/main/skills/09-%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E4%B8%8E%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD/torch-geometric
Command: npx skills add https://github.com/qinyan-ai/qinyan-academic-skills --skill torch-geometric-qinyan-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires torch, torch_geometric, numpy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

PyG provides a comprehensive, efficient toolkit for building, training, and evaluating Graph Neural Networks on a variety of data types.

Core Features & Use Cases

  • Node and graph classification, link prediction, and heterogeneous graphs using a suite of ready-to-use layers and datasets.
  • Rapid experimentation with templates and examples for molecular property prediction, social networks, knowledge graphs, and more.
  • Large-scale graph processing and multi-GPU support with PyG's data handling and training utilities.

Quick Start

Install PyG, import the library, and run a minimal GCN example on a standard dataset.

Frequently Asked Questions about torch-geometric

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

FAQPage Schema
How do I build and train a Graph Neural Network for node classification?▼

To build a Graph Neural Network for node classification, use this Skill to apply ready-to-use GNN layers and datasets. It provides an end-to-end workflow from data loading to model evaluation for standard graph tasks.

What's the best way to benchmark GNN models on molecular property prediction?▼

Benchmarking GNN models on molecular property prediction is facilitated through rapid experimentation templates. The Skill provides examples for chemistry and biology domains to evaluate graph classification workflows efficiently.

Can I use PyTorch to handle heterogeneous graphs and link prediction?▼

Yes, you can use PyTorch to handle heterogeneous graphs and link prediction. The Skill supports these specific graph types alongside node classification using its comprehensive data handling utilities.

Does this GNN toolkit support large-scale graph processing and multi-GPU environments?▼

Large-scale graph processing and multi-GPU support are available through PyG's data handling and training utilities. This allows efficient computation for substantial graph datasets across multiple GPUs.

What domains are supported for applying Graph Neural Networks?▼

Graph Neural Networks can be applied across domains like biology, chemistry, social networks, and knowledge graphs. The Skill facilitates end-to-end workflows from data loading to model evaluation for these fields.

Related Skills

Explore More Education & Research Skills→
garochee33garochee33
3

Compute

Accelerate numerical, scientific, GPU, and quantum computation workflows with NumPy, SciPy, Numba, Torch, and Qiskit.

Community
Advanced
ricablericable
1

ruvector-gnn-wasm

Provides WebAssembly-compiled Graph Neural Network inference for browsers and edge devices.

Community
Advanced
jasrajtulsijasrajtulsi

torch-geometric

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

Community
Advanced
jackspacejackspace
16

torch-geometric

Develop and train graph neural networks with PyTorch Geometric.

Community
Advanced