This is a collection of graph neural network (GNN) resources. GNN is a class of machine learning neural network methods that are best represented with graph data structures. ## Contents - [[Graph Neural Networks#Videos | Videos]] - [[Graph Neural Networks#Repos | Repos]] - [[Graph Neural Networks#Readings| Readings]] - [[Graph Neural Networks#Courses| Courses]] - [[Graph Neural Networks#Textbooks| Textbooks]] ### Videos #### Petar Veličković Petar's advisor was Jure Leskovic and he now is a senior research scientist at Deep Mind. Petar also put together some useful resources in a [twitter thread](https://twitter.com/PetarV_93/status/1306689702020382720) — some of them are below. 😄 <iframe width="560" height="315" src="https://www.youtube.com/embed/uF53xsT7mjc" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> #### Michael Bronstein Michael Bronstein ~~is~~ was the head of graph learning at Twitter (2019-2013) and is a professor at the Imperial College London. <iframe width="560" height="315" src="https://www.youtube.com/embed/w6Pw4MOzMuo" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> #### Xavier Bresson Xavier Bresson gives an overview of the field as a guest lecturer at NYU. <iframe width="560" height="315" src="https://www.youtube.com/embed/Iiv9R6BjxHM" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> #### Microsoft Introduction <iframe width="560" height="315" src="https://www.youtube.com/embed/zCEYiCxrL_0" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> ### Repos - [DAIR AI GNNs Recipe](https://github.com/dair-ai/GNNs-Recipe) ### Readings #### Survey papers - [Graph Neural Networks: Methods, Applications, and Opportunities](https://arxiv.org/abs/2108.10733) (Lilapati Waikhom, Ripon Patgiri) - [A Comprehensive Survey on Graph Neural Networks](https://arxiv.org/abs/1901.00596) (Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, Philip S. Yu) #### Blog posts - [Michael Bronstein's *Geometric Deep Learning*](https://towardsdatascience.com/geometric-foundations-of-deep-learning-94cdd45b451d) - [Amal Menzli's *Graph Neural Network and Some of GNN Applications: Everything You Need to Know*](https://neptune.ai/blog/graph-neural-network-and-some-of-gnn-applications) - [Eric J. Ma's *An attempt at demystifying graph deep learning*](https://ericmjl.github.io/essays-on-data-science/machine-learning/graph-nets/) - [Rishabh Anand's *An Illustrated Guide to Graph Neural Networks*](https://medium.com/dair-ai/an-illustrated-guide-to-graph-neural-networks-d5564a551783) - [Distill's *A Gentle Introduction to Graph Neural Networks*](https://distill.pub/2021/gnn-intro/) - [Distill's *Understanding Convolutions on Graphs*](https://distill.pub/2021/understanding-gnns/) - [Thomas Kipf's *Graph Convolutional Networks*](http://tkipf.github.io/graph-convolutional-networks/) ### Courses - [Jure Leskovic's CS224W @ Standford](https://web.stanford.edu/class/cs224w/) - [William L. Hamilton's COMP 766 @ McGill](https://cs.mcgill.ca/~wlh/comp766/) ### Textbooks - [William L. Hamilton's _Graph Representation Learning Book_](https://www.cs.mcgill.ca/~wlh/grl_book/) --- #### Related #machine_learning #neural_networks #GNNs