Covers: theory of Graph Neural Networks
Estimated time needed to finish: 180 minutes
Questions this item addresses:
  • How can i learn a lot about graphs?
How to use this item?

The videos and some slides from the workshop at Stanford are posted here. You can check out the topics you're interested in

Author(s) / creator(s) / reference(s)
0 comment

Getting Started With Graph Neural Networks

Total time needed: ~10 hours
This recipe provides an overview of Graph Neural Networks and various applications they enable
Potential Use Cases
relationship preiction, recommender systems, atribute classification, drug discovery, physics based simulations
Who is This For ?
INTERMEDIATEML Developers and Data Scientists familiar with basics of ML
Click on each of the following annotated items to see details.
VIDEO 1. Introduction to Graphs
  • What are Graph Neural Networks?
2 minutes
RECIPE 2. Graph Data, Representations, and Tasks
47 minutes
RECIPE 3. Node Classification using Graph Neural Networks
73 minutes
RECIPE 4. Link Prediction using Graph Neural Networks
60 minutes
REPO 5. Heterogeneous Graphs
  • How to deal with Heterogeneous nodes on graphs?
20 minutes
VIDEO 6. CS224W: Machine Learning with Graphs Playlist
  • What can you do with ML on graphs?
3 hours
BOOK_CHAPTER 7. Graph Neural Networks in Action
10 minutes
ARTICLE 8. A Gentle Introduction to Graph Neural Networks
  • What are GNNs used for?
10 minutes
ARTICLE 9. Understanding Convolutions on Graphs
  • How can convolutions be used on graph data?
10 minutes
VIDEO 10. A Literature Review on Graph Neural Networks
10 minutes
VIDEO 11. Overview of Machine Learning for Knowledge Graphs
10 minutes
VIDEO 12. TGN: Temporal Graph Networks for Deep Learning on Dynamic Graphs
10 minutes
VIDEO 13. Inductive Representation Learning on Temporal Graphs
10 minutes
VIDEO 14. [GAT] Graph Attention Networks
10 minutes
VIDEO 15. [GATA] Learning Dynamic Belief Graphs to Generalize on Text-Based Games
10 minutes
VIDEO 16. Learning to Represent Programs with Graphs
10 minutes
VIDEO 17. SELFIES: A 100% robust representation of semantically constrained Graphs, for deep generative models
10 minutes
VIDEO 18. Junction Tree Variational Autoencoder for Molecular Graph Generation
10 minutes
VIDEO 19. [hgraph2graph] Hierarchical Generation of Molecular Graphs using Structural Motifs
10 minutes
VIDEO 20. Learning Mesh-Based Simulation with Graph Networks
10 minutes
VIDEO 21. Learning to Simulate Complex Physics with Graph Networks
10 minutes
VIDEO 22. Meta-Graph: Few-Shot Link Prediction Using Meta-Learning
10 minutes
VIDEO 23. Memory-Based Graph Networks
10 minutes
VIDEO 24. Principal Neighbourhood Aggregation for Graph Nets
10 minutes
VIDEO 25. Learning Discrete Structures for Graph Neural Networks
10 minutes
VIDEO 26. Representation Learning of Histopathology Images using Graph Neural Networks
10 minutes
VIDEO 27. Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph
10 minutes
VIDEO 28. Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer
10 minutes
VIDEO 29. Nodes, Edges and Properties; Graph Analysis Intro for ML Newcomers
10 minutes
OTHER 30. Stanford Graph Learning Workshop 2021
  • How can i learn a lot about graphs?
3 hours

Concepts Covered

Ashok Tak.
I don't know how I can update the recipes but I think these articles published today should be part of this recipe, at least the Introduction one. 1. 2.
Amir Feizpour.
Ashok Tak. funnily enough I marked these 2 to add them to the recipe. I'll add them later today. if there are other resources you think we should add ping me and I'll add you as a collaborator so that you can add those directly