- Graph Representation Learing: A great introductory book on graph neural networks.
- Network Science (Chapter 2, Graph Theory): A very well written explanation of the basis of the graph theory.
- Relational inductive biases, deep learning, and graph networks: A DeepMind article that introduces a general approach for learning on graphs.
- Graph convolutional networks: The first paper that presented graph convolutional networks.
- Graph attention networks: The paper that demonstrates the graph attention networks.
- Inductive representation learning on large graphs: A paper on inductive learning with graphs.
- PyTorch Geometric: One of the best libraries for deep learning with graphs.
- Einsum notation: A good post about Einsum notation that is used everywhere in deep learning.
- Weisfeiler-Lehman isomorphism test: A well-written explanation of the Weisfeiler-Lehman isomorphism test.
- Colab 0: Introduction to graph theory: Introduction, basic properties of graphs.
- Colab 1: Graph convolutions: Hands-on guide to graph convolutions.
- Colab 2: PyTorch Geometric and node level tasks: Introduction to PyG via semi-supervised node classification.
- Colab 3: Generalized message passing: Generalized message passing algorithm.