# GNN material/tutorials

## Torch Geometric

### Tutorials
The official tutorials and intros are pretty good. The colab notebooks follow logically and are a great starting point:
https://pytorch-geometric.readthedocs.io/en/latest/notes/colabs.html
From our perspective the important ones are:
1. [General intro](https://colab.research.google.com/drive/1h3-vJGRVloF5zStxL5I0rSy4ZUPNsjy8?usp=sharing)
2. [Node classification](https://colab.research.google.com/drive/14OvFnAXggxB8vM4e8vSURUp1TaKnovzX?usp=sharing)
3. [Graph classification](https://colab.research.google.com/drive/1I8a0DfQ3fI7Njc62__mVXUlcAleUclnb?usp=sharing)
4. [Scaling GNNs](https://colab.research.google.com/drive/1XAjcjRHrSR_ypCk_feIWFbcBKyT4Lirs?usp=sharing) This one is not compulsory but may be useful.

### Video tutorials
There is a very extensive video tutorial. I went through some of the videos (but not all) and the content is really high quality
https://github.com/AntonioLonga/PytorchGeometricTutorial

## Papers and books

| Title | Link | Notes |
|:-----------------------------------------------------------:| ----------------------------------------- |:---------------------------:|
| Representation Learning on Graphs: Methods and Applications | [click](https://arxiv.org/abs/1709.05584) | A foundational review paper |
| Graph Attention Networks | [click](https://arxiv.org/abs/1710.10903) | We use those in DONNA |
| GRL book | [click](https://www.cs.mcgill.ca/~wlh/grl_book/) | a great first read introduction |