We have prepared a list of colab notebooks that practically introduces you to the world of Graph Neural Networks with PyG:
- Introduction: Hands-on Graph Neural Networks
- Node Classification with Graph Neural Networks
- Graph Classification with Graph Neural Networks
- Scaling Graph Neural Networks
- Point Cloud Classification with Graph Neural Networks
- Explaining GNN Model Predictions using Captum
- Customizing Aggregations within Message Passing
- Node Classification with Graph Neural Networks Instrumented with Weights and Biases Logging and Sweeps
- Link Prediction on MovieLens
All colab notebooks are released under the MIT license.
Stanford CS224W Graph ML Tutorials:
The Stanford CS224W course has collected a set of graph machine learning tutorial blog posts, fully realized with PyG. Students worked on projects spanning all kinds of tasks, model architectures and applications. All tutorials also link to a Google Colab with the code in the tutorial for you to follow along with as you read it!
PyTorch Geometric Tutorial Project:
The PyTorch Geometric Tutorial project provides video tutorials and Colab notebooks for a variety of different methods in PyG:
- Introduction [Video, Notebook]
- PyTorch basics [Video, Notebook]
- Graph Attention Networks (GATs) [Video, Notebook]
- Spectral Graph Convolutional Layers [Video, Notebook]
- Aggregation Functions in GNNs [Video, Notebook]
- (Variational) Graph Autoencoders (GAE and VGAE) [Video, Notebook]
- Adversarially Regularized Graph Autoencoders (ARGA and ARGVA) [Video, Notebook]
- Graph Generation [Video]
- Recurrent Graph Neural Networks [Video, Notebook (Part 1), Notebook (Part 2)]
- DeepWalk and Node2Vec [Video (Theory), Video (Practice), Notebook]
- Edge analysis [Video, Notebook (Link Prediction), Notebook (Label Prediction)]
- Data handling in PyG (Part 1) [Video, Notebook]
- Data handling in PyG (Part 2) [Video, Notebook]
- MetaPath2vec [Video, Notebook]
- Graph pooling (DiffPool) [Video, Notebook]