Session 09
Graph Clustering
DRAFT: This content is under development. Check back closer to the course start date.
Learning Objectives
- Define community structure and explain when graph clustering is the right tool
- Apply modularity-based methods (Louvain, Leiden) and understand what they optimize
- Use label propagation and spectral clustering; compare their assumptions
- Evaluate clustering results when ground-truth communities are not available
Topics
- Community detection and modularity
- Louvain and Leiden algorithms
- Label propagation
- Spectral clustering on graphs
- Evaluation without ground truth