Logo
2.0.0

Notes

  • Installation
    • Quick Start
    • Installation via Anaconda
    • Installation via Pip Wheels
    • Installation from Source
    • Frequently Asked Questions
  • Introduction by Example
    • Data Handling of Graphs
    • Common Benchmark Datasets
    • Mini-batches
    • Data Transforms
    • Learning Methods on Graphs
  • Creating Message Passing Networks
    • The “MessagePassing” Base Class
    • Implementing the GCN Layer
    • Implementing the Edge Convolution
  • Creating Your Own Datasets
    • Creating “In Memory Datasets”
    • Creating “Larger” Datasets
    • Frequently Asked Questions
  • Heterogeneous Graph Learning
    • Example Graph
    • Creating Heterogeneous Graphs
    • Heterogeneous Graph Transformations
    • Creating Heterogeneous GNNs
    • Heterogeneous Graph Samplers
  • Loading Graphs from CSV
  • Managing Experiments with GraphGym
    • Highlights
    • Why GraphGym?
    • Basic Usage
    • In-Depth Usage
    • Customizing GraphGym
  • Advanced Mini-Batching
    • Pairs of Graphs
    • Bipartite Graphs
    • Batching Along New Dimensions
  • Memory-Efficient Aggregations
  • TorchScript Support
    • Converting GNN Models
    • Creating Jittable GNN Operators
  • GNN Cheatsheet
    • Graph Neural Network Operators
    • Heterogeneous Graph Neural Network Operators
    • Hypergraph Neural Network Operators
    • Point Cloud Neural Network Operators
  • Colab Notebooks
  • External Resources

Package Reference

  • torch_geometric
  • torch_geometric.nn
    • Convolutional Layers
    • Dense Convolutional Layers
    • Normalization Layers
    • Global Pooling Layers
    • Pooling Layers
    • Dense Pooling Layers
    • Unpooling Layers
    • Models
    • Functional
    • Model Transformations
    • DataParallel Layers
  • torch_geometric.data
  • torch_geometric.loader
  • torch_geometric.datasets
  • torch_geometric.transforms
  • torch_geometric.utils
  • torch_geometric.graphgym
    • Workflow Modules
    • Model Modules
    • Register Modules
    • Utility Modules
  • torch_geometric.profile
pytorch_geometric
  • »
  • Colab Notebooks
  • Edit on GitHub

Colab Notebooks¶

We have prepared a list of colab notebooks that practically introduces you to the world of Graph Neural Networks with PyG:

  1. Introduction: Hands-on Graph Neural Networks

  2. Node Classification with Graph Neural Networks

  3. Graph Classification with Graph Neural Networks

  4. Scaling Graph Neural Networks

  5. Point Cloud Classification with Graph Neural Networks

  6. Explaining GNN Model Predictions using Captum

Next Previous

© Copyright 2021, Matthias Fey. Revision c5152eae.

Built with Sphinx using a theme provided by Read the Docs.