https://github.com/filippomb/tutorial_gnn_explainability
This in an introduction to PyTorch Geometric, the deep learning library for Graph Neural Networks, and to interpretability tools for analyzing the decision process of a GNN.
https://github.com/filippomb/tutorial_gnn_explainability
captum explainability explainable-ai geometric-deep-learning graph-neural-networks pytorch-geometric tutorial tutorial-code
Last synced: 3 months ago
JSON representation
This in an introduction to PyTorch Geometric, the deep learning library for Graph Neural Networks, and to interpretability tools for analyzing the decision process of a GNN.
- Host: GitHub
- URL: https://github.com/filippomb/tutorial_gnn_explainability
- Owner: FilippoMB
- License: mit
- Created: 2023-11-22T13:19:50.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2025-03-15T10:34:57.000Z (11 months ago)
- Last Synced: 2025-03-15T11:27:10.368Z (11 months ago)
- Topics: captum, explainability, explainable-ai, geometric-deep-learning, graph-neural-networks, pytorch-geometric, tutorial, tutorial-code
- Language: Jupyter Notebook
- Homepage:
- Size: 2.72 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Introduction to Graph Neural Networks and Explainability
This is a gentle introduction to building a Graph Neural Network with [PyTorch Geometric](https://pytorch-geometric.readthedocs.io/en/latest/), the popular library for geometric deep learning.
The tutorial will also cover some streamlined interpretability tools for analyzing the decision process of a GNN.
The tutorial is a Python notebook that you can
[](https://nbviewer.org/github/FilippoMB/Tutorial_GNN_explainability/blob/main/tutorial.ipynb)
or [](https://colab.research.google.com/github/FilippoMB/Tutorial_GNN_explainability/blob/main/tutorial.ipynb)
---
To run the notebook locally, you need the following libraries:
```
- PyTorch
- PyTorch Geometric
- Pytorch Lightning
- Captum
- Networkx
```
---
This tutorial is adapted from the tutorial of [Simone Scardapane](https://www.sscardapane.it/) ([slides](https://docs.google.com/presentation/d/103YA-dJ9PO9iSyUxoY-xbJhVu6VrEsMvvw4rBe6QBwY/edit#slide=id.g1e3b33a1319_0_0), [notebook](https://colab.research.google.com/drive/1nV44NrNqcXC2thU6-zzxnJPnIalo870m)).