Deep Learning / 22
Graph Neural Networks
Follow graph data through message passing and aggregation into node, edge, and graph tasks.
This is a knowledge index. Published titles open their articles; the remaining entries outline planned coverage.
Subtopics
- 22.01
Graph Data
Planned guide: Graph Data. Focus on intuition, assumptions, and a worked example.
- 22.02
Nodes
Planned guide: Nodes. Focus on intuition, assumptions, and a worked example.
- 22.03
Edges
Planned guide: Edges. Focus on intuition, assumptions, and a worked example.
- 22.04
Node Features
Planned guide: Node Features. Focus on intuition, assumptions, and a worked example.
- 22.05
Message Passing
Planned guide: Message Passing. Focus on intuition, assumptions, and a worked example.
- 22.06
Neighborhood Aggregation
Planned guide: Neighborhood Aggregation. Focus on intuition, assumptions, and a worked example.
- 22.07
Graph Convolutional Networks
Planned guide: Graph Convolutional Networks. Focus on intuition, assumptions, and a worked example.
- 22.08
Graph Attention Networks
Planned guide: Graph Attention Networks. Focus on intuition, assumptions, and a worked example.
- 22.09
GraphSAGE
Planned guide: GraphSAGE. Focus on intuition, assumptions, and a worked example.
- 22.10
Node Classification
Planned guide: Node Classification. Focus on intuition, assumptions, and a worked example.
- 22.11
Link Prediction
Planned guide: Link Prediction. Focus on intuition, assumptions, and a worked example.
- 22.12
Graph Classification
Planned guide: Graph Classification. Focus on intuition, assumptions, and a worked example.
- 22.13
GNN Oversmoothing
Planned guide: GNN Oversmoothing. Focus on intuition, assumptions, and a worked example.
- 22.14
GNN Applications
Planned guide: GNN Applications. Focus on intuition, assumptions, and a worked example.