Primers • Graph Neural Networks

• Background: Graph Neural Networks
• Gentle Introduction to GNNs
• Survey Papers on GNNs
• Diving Deep into GNNs
• GNN Papers and Implementations
• Benchmarks and Datasets
• Tools
• Citation

Background: Graph Neural Networks

• Graph neural networks (GNNs) are rapidly advancing progress in ML for complex graph data applications. I’ve composed this concise recipe dedicated to students who are lookin to learn and keep up-to-date with GNNs. It’s non-exhaustive but it aims to get students familiar with the topic.

Gentle Introduction to GNNs

• There are several introductory content to learn about GNNs. The following are some useful ones:

  • Foundations of GNNs (by Petar Veličković)
  • Gentle Introduction to GNNs (by Distill)
  • Understanding Convolutions on Graphs (by Distill)
  • Graph Convolutional Networks (by Thomas Kipf)

Survey Papers on GNNs

• Here are two fantastic survey papers on the topic to get a broader and concise picture of GNNs and recent progress:
  • Graph Neural Networks: Methods, Applications, and Opportunities (by Lilapati Waikhom and Ripon Patgiri)
  • [A] Comprehensive Survey on Graph Neural Networks](https://arxiv.org/abs/1901.00596) (by Zonghan Wu et al.)

Diving Deep into GNNs

• After going through quick high-level introductory content, here are some great material to go deep:
  • Geometric Deep Learning (by Michael Bronstein et al.)
  • Graph Representation Learning Book (by William Hamilton)
  • CS224W: ML with Graphs (by Jure Leskovec)

GNN Papers and Implementations

• If you want to keep up-to-date with popular recent methods and paper implementations for GNNs, the Papers with Code community maintains this useful collection:
  • Graph Models by Papers with Code

Benchmarks and Datasets

• If you are interested in benchmarks/leaderboards and graph datasets that evaluate GNNs, the Papers with Code community also maintains such content here:
  • Datasets by Papers with Code
  • Graph Benchmarks by Papers with Code

Tools

• Here are a few useful tools to get started with GNNs:
  • PyTorch Geometric
  • Deep Graph Library
  • jraph
  • Spektral

Citation

If you found our work useful, please cite it as:

@article{Chadha2020DistilledGraphNeuralNetworks,
  title   = {Graph Neural Networks},
  author  = {Chadha, Aman},
  journal = {Distilled AI},
  year    = {2020},
  note    = {\url{https://aman.ai}}
}