What is linkage in agglomerative clustering?
hardAnswer
- Linkage defines the distance between two clusters.
- Single linkage = min pairwise distance (chains, elongated clusters).
- Complete linkage = max pairwise distance (compact clusters, sensitive to outliers).
- Average linkage = mean pairwise distance.
- Ward linkage minimizes within-cluster variance (produces balanced, compact clusters — most common default).
Check yourself — multiple choice
- Ward linkage maximizes within-cluster variance
- Single linkage produces compact, spherical clusters
- Ward linkage minimizes within-cluster variance
- Complete linkage ignores outliers
Ward is the variance-minimizing linkage — the usual default.
#clustering
Practise Unsupervised Learning
214 interview questions in this topic.