Spectral Clustering

Fact

A method that groups items using eigenvectors from a similarity graph.

In Plain Words

Spectral clustering is like sorting a messy school cafeteria. You ignore the table rows and watch who keeps trading fries.

It builds a similarity map, then finds groups in that map. It helps split images and spot circles in social networks.

Related Concepts

• Clustering
• Unsupervised Learning
• k-Means Clustering
• Dimensionality Reduction

Clustering
Spectral Clustering is a way to put similar items into groups.

Unsupervised Learning
Spectral Clustering usually groups data without human labels.

K-Means Clustering
After spectral embedding, K-Means Clustering often makes the final groups.

Dim. Reduction
Spectral Clustering first turns the similarity graph into a smaller space.