Fast and eager k-medoids clustering: O(k) runtime improvement of the PAM, CLARA, and CLARANS algorithms.
Erich SchubertPeter J. RousseeuwPublished in: Inf. Syst. (2021)
Keyphrases
- significant improvement
- data clustering
- clustering algorithm
- theoretical analysis
- k means
- machine learning
- orders of magnitude
- benchmark datasets
- worst case
- computational cost
- data structure
- nearest neighbor
- computationally efficient
- decision trees
- document clustering
- neural network
- graph theory
- data mining tasks
- synthetic and real datasets