// ⌬ Graph Neural Networks & AI for Science
Graph Neural Networks (GCN / GAT)
Nodes update by aggregating their neighbors' features.
图神经网络（GCN / GAT） 2016 Intermediate core
IN PLAIN WORDS
GCN averages normalized neighbor messages; GAT weights neighbors with attention. Used for molecules, social networks, recommendation and traffic.
Used in: Drug discovery, recommendation, knowledge graphs
TIMELINE · prerequisites → this → what builds on it
01Original paper
Semi-Supervised Classification with Graph Convolutional Networks
Thomas N. Kipf, Max Welling · 2016
arXiv ↗ ✓ Verified · arXiv API
Note: GAT：arXiv:1710.10903（2017）
02Where it sits
Learn the left column first; the right column builds on this one.
Related:Transformer & Self-Attention
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
Explainers
Official docs
Courses
04Where the course teaches it
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
gnn)