Adding tutorial on Graph Neural Networks #21
Conversation
| @@ -0,0 +1,3 @@ | |||
| <?xml version="1.0" encoding="UTF-8"?> | |||
There was a problem hiding this comment.
this need to be check if the image is inserted in the notebook or we need to copy separately...
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
pls loop me in next time 🐰 |
| ok, the wheels do not help much as they are missing patch PT versions, see pyg-team/pytorch_geometric#2735 |
| @phlippe seems all remaining issues were resolved, shall we run more training epochs as now the tests take a few minutes only |
| # In this tutorial, we will discuss the application of neural networks on graphs. | ||
| # Graph Neural Networks (GNNs) have recently gained increasing popularity in both applications and research, including domains such as social networks, knowledge graphs, recommender systems, and bioinformatics. | ||
| # While the theory and math behind GNNs might first seem complicated, the implementation of those models is quite simple and helps in understanding the methodology. | ||
| # Therefore, we will discuss the implementation of basic network layers of a GNN, namely graph convolutions, and attention layers. | ||
| # Finally, we will apply a GNN on a node-level, edge-level, and graph-level tasks. | ||
| # | ||
| # Below, we will start by importing our standard libraries. |
There was a problem hiding this comment.
I think this is rather description, note that description is added to the notebook
There was a problem hiding this comment.
Good point. The paragraph is now removed from the notebook and merged into the description in the .meta.yaml file.
Great to hear! The notebook loads pre-trained models so that it only runs evaluations. However, if we comment out the download of the pre-trained models, we can check whether a training also works. |
4 participants
Before submitting
-> This PR was discussed with @tchaton in the PL Slack channel.
What does this PR do?
This PR adds a new tutorial on Graph Neural Networks with PyTorch Lightning. This tutorial discusses fundamentals on GNNs, such as Graph Convolutions and Graph Attention layers. It also includes a section on experiments for semi-supervised node classification and molecule generalization. The tutorial is an adapted version of the original GNN tutorial for the Deep Learning course at the University of Amsterdam (link).
The png and svg files are images that are included in the notebook.
PR review
Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.
Did you have fun?
Make sure you had fun coding 🙃