Welcome to the world of Graph Neural Networks (GNNs)! This repository is designed to introduce beginners to GNNs and provide a series of tutorials on various techniques in Geometric Machine Learning. Whether you're a student, developer, or researcher, this resource will help you understand how GNNs work and how to implement them using the PyTorch Geometric library.
To run these tutorials, you'll need the following dependencies:
- PyTorch: Install PyTorch for deep learning capabilities.
- Anaconda: Use Anaconda for managing Python environments.
- PyTorch Geometric (PyG): Follow the installation instructions provided in the PyG documentation.
- NetworkX: Install NetworkX for graph-related operations.
This repository offers a series of tutorials to help you grasp the concepts of Graph Neural Networks (GNNs) and how to apply them using PyTorch Geometric:
-
NetworkX Graph Tutorial: Learn about NetworkX and its applications in graph-related operations.
-
Node Embedding Pipeline: Explore a comprehensive pipeline for node embedding in graph data.
-
PyTorch Geometric Tutorial: Dive into practical GNN implementation using PyTorch Geometric, covering advanced techniques in the GNN field.
For more information and resources on GNNs and their implementation using PyTorch Geometric, you can refer to the following:
- PyTorch Geometric documentation: Official documentation of PyTorch Geometric.
- NetworkX documentation: Official documentation of NetworkX.
- Stanford University’s Machine Learning with Graphs course: A playlist of lectures on Machine Learning with Graphs offered by Stanford University.
We welcome contributions to this project.
This project is licensed under the MIT License.