A simple and fast algorithm for K-medoids clustering

By Hae-Sang Park, Chi-Hyuck Jun. 2009

2,087 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers (2021, methodology): “We choose K-medoids (Park and Jun, 2009) in this work for easy interpretation of clustering results.”
An Active Learning Method Using Clustering and Committee-Based Sample Selection for Sound Event Classification (2018, methodology): “K-medoids [19, 20] is a partitioning-based clustering algorithm, similar to more widely-used K-means.”
Faster k-Medoids Clustering: Improving the PAM, CLARA, and CLARANS Algorithms (2018, methodology): “Park and Jun (2009) propose a “ k -means like” algorithm for k -medoids (which actually was already considered by Reynolds et al. 2006 before), where in each iteration the medoid is chosen to be the object with the smallest distance sum to other members of the cluster, then each point is assigned…”
Multi-task Learning with Labeled and Unlabeled Tasks (2016, methodology): “Active DA-SS involves the minimization of the k -medoid risk (17), which we perform using a local search as in [30].”
Molecular Docking: Shifting Paradigms in Drug Discovery (2019, methodology): “Then, they performed clustering via the K-medoids method on the calculated molecular dynamics trajectories [88] to identify MD-derived representative conformations of the investigated targets.”
Generalized Low Rank Models (2014, methodology): “For example, k-mediods [71, 110] is obtained by using ̧1 loss in place of quadratic loss in the quadratic clustering problem.”
A Comprehensive Survey of Clustering Algorithms (2015, background): “K-means [7] and K-medoids [8] are the two most famous ones of this kind of clustering algorithms.”
Survey on the Usage of Machine Learning Techniques for Malware Analysis (2017, background): “3, apply to k-medoids as well, but it is less sensitive to outliers [84].”
Persistence Images: A Stable Vector Representation of Persistent Homology (2015, methodology): “’ indicates concatenated H0 and H1 information. features across the classes. We utilize this data for a variety of tasks: (1) comparing classiﬁcation accuracy–using the clustering algorithm K-medoids [20, 21]–for the PD framework equipped with the bottleneck distance and the PI framework equipped wi”
Unsupervised extraction of functional gene expression signatures in the bacterial pathogen Pseudomonas aeruginosa with eADAGE (2016, methodology): “We clustered this distance matrix using the Partition Around Medoids (PAM) clustering algorithm (Park & Jun, 2009).”
A review of moving object trajectory clustering algorithms (2016, background): “Two improved editions are given in Amorim and Mirkin (2012) and k-medoids (Park and Jun 2009).”