Getting Started with Graph Neural Networks

Here, you’ll find a few resources that’ll get you started with Graph Neural Networks. I will keep updating it so you can always check back!.

Intro to graph representation learning

1. Representation learning on graphs: Methods and Applications; Hamilton et al.
2. Graph Neural Networks: A review or methods and applications; Zhou et al;
3. Deep Learning on graphs: A survey; Ziwei Zhang et al

Books:

1. Graph Representation learning book; Will Hamilton (Highly recommended for comprehensive understanding)
2. Geometric Deep Learning Grids, Groups, Graphs, Geodesics, and Gauges; Bronstein et al

Video:

1. Machine Learning with Graphs; Jure Leskovec (Stanford University), Videos, Course website

Important to know architectures

1. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering (ChebNet); Deferrard et al
2. Graph Convolutional Neural Networks; Kipf et al.
3. Graph Attention Networks (GAT); Velickovic et al.
4. Inductive Representation learning in large graphs; Hamilton et al
5. Graph Isormorphism Networks; Xu et al.
6. Gated Graph Sequence Neural Networks; Li et al
7. Benchmarking Graph Neural Networks; Dwivedi et al

Frameworks/ tools

1. PyTorch Geometric (Based on pytorch)
2. Spekral (Tensorflow/ keras)
3. Deep Graph Library (Framework agnostic, compatible with PyTorch, Tensorflow, MxNet etc)
4. Open Graph Benchmark: Datasets for Machine Learning on graphs