@inproceedings{176ce87948384eea9496d26c165e63f2,

title = "A distributed shared nearest neighbors clustering algorithm",

abstract = "Current data processing tasks require efficient approaches capable of dealing with large databases. A promising strategy consists in distributing the data along several computers that partially solves the undertaken problem. Then, these partial answers are integrated in order to obtain a final solution. We introduce the Distributed Shared Nearest Neighbor based clustering algorithm (D-SNN) which is able to work with disjoint partitions of data producing a global clustering solution that achieves a competitive performance regarding centralized approaches. Our algorithm is suited for large scale problems (e.g, text clustering) where data cannot be handled by a single machine due to memory size constraints. Experimental results over five data sets show that our proposal is competitive in terms of standard clustering quality performance measures.",

keywords = "Clustering, Distributed algorithm, Shared nearest neighbors",

author = "Juan Zamora and H{\'e}ctor Allende-Cid and Marcelo Mendoza",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG, part of Springer Nature 2018.; 22nd Iberoamerican Congress on Pattern Recognition, CIARP 2017 ; Conference date: 07-11-2017 Through 10-11-2017",

year = "2018",

doi = "10.1007/978-3-319-75193-1_85",

language = "English",

isbn = "9783319751924",

series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",

publisher = "Springer Verlag",

pages = "710--718",

editor = "Sergio Velastin and Marcelo Mendoza",

booktitle = "Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications - 22nd Iberoamerican Congress, CIARP 2017, Proceedings",

}