k-medoids vs k-means — the difference.

medium

Answer

$k-medoids uses actual data points as cluster representatives (medoids) instead of arithmetic means.$
$Robust to outliers (the median is more robust than the mean).$
$Works with any distance/dissimilarity — not just Euclidean (categorical, custom).$
$O(k(n - k)^{2})$
$Use for outlier-heavy data or non-Euclidean distances.$

Check yourself — multiple choice

Same as k-means
Medoids = actual data points → robust to outliers + supports any distance; slower (PAM: $O(k(n - k)^{2})$ )
Only Euclidean
Random

k-medoids: robust to outliers, arbitrary distance; slower than k-means.

#clustering

214 interview questions in this topic.