Graph Neural Networks & Message Passing Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Graphs are the natural language for molecules, social networks, and hardware. This list traces message passing from spectral convolutions through attention and pooling, focusing on architectures that actually scale and theory that explains when they fail.

Graph Neural Networks & Message Passing: 10 key papers

1. Semi-Supervised Classification with Graph Convolutional Networks
   Kipf and Welling. arXiv 2016.
2. Graph Attention Networks
   Veličković et al. arXiv 2017.
3. How Powerful are Graph Neural Networks?
   Xu et al. arXiv 2018.
4. Neural Message Passing for Quantum Chemistry
   Gilmer et al. arXiv 2017.
5. Modeling Relational Data with Graph Convolutional Networks
   Schlichtkrull et al. arXiv 2017.
6. Simplifying Graph Convolutional Networks
   Wu et al. arXiv 2019.
7. Representation Learning on Graphs with Jumping Knowledge Networks
   Xu et al. arXiv 2018.
8. Relational inductive biases, deep learning, and graph networks
   Battaglia et al. arXiv 2018.
9. Inductive Representation Learning on Large Graphs
   Hamilton et al. arXiv 2017.
10. A Comprehensive Survey on Graph Neural Networks
    Wu et al. arXiv 2019.

Related reading lists

• Knowledge Distillation
• Memory-Augmented RL & Recurrent Policies
• Neural Operators & PDE Solvers
• Swarm RL & Collective Behavior
• Chain-of-Thought & Reasoning
• Communication in Multi-Agent RL
• Causal Discovery & Structure Learning
• Long-Context & Memory Transformers