Abstract:
We’ll go over graph neural networks (GNN) that has been gaining popularity over the last few years. We will cover the definition, some different models of the similar flavor, and if time permits some coding examples on how one can use them for your purpose.
Resources:
https://web.stanford.edu/class/cs224w/slides/03-GNN1.pdf here is the slides going over basics of GCN
https://web.stanford.edu/class/cs224w/slides/04-GNN2.pdf the slides going over the more general framework of message passing GNN
https://colab.research.google.com/drive/1h3-vJGRVloF5zStxL5I0rSy4ZUPNsjy8?usp=sharing colab spreadsheet that you can follow to see how to use GNNs!
https://distill.pub/2021/understanding-gnns/ has an interactive example near bottom of the page that you can test out simple examples of GCN/GAT/GraphSage/GIN
https://openreview.net/pdf?id=B1l2bp4YwS here is the paper on what GNN can do/not