Scalable model-based clustering for large databases based on data summarization

Document Type

Journal article

Source Publication

IEEE Transactions on Pattern Analysis & Machine Intelligence

Publication Date

2015

Volume

27

Issue

11

First Page

1710

Last Page

1719

Keywords

Scalable clustering; Gaussian mixture model; expectation-maximization; data summary; maximum penalized likelihood estimate

Abstract

The scalability problem in data mining involves the development of methods for handling large databases with limited computational resources such as memory and computation time. In this paper, two scalable clustering algorithms, bEMADS and gEMADS, are presented based on the Gaussian mixture model. Both summarize data into subclusters and then generate Gaussian mixtures from their data summaries. Their core algorithm, EMADS, is defined on data summaries and approximates the aggregate behavior of each subcluster of data under the Gaussian mixture model. EMADS is provably convergent. Experimental results substantiate that both algorithms can run several orders of magnitude faster than expectation-maximization with little loss of accuracy.

DOI

10.1109/TPAMI.2005.226

Print ISSN

01628828

E-ISSN

19393539

Publisher Statement

Copyright © 2005 Institute of Electrical and Electronics Engineers.

Access to external full text or publisher's version may require subscription.

Full-text Version

Publisher’s Version

Language

English

Recommended Citation

Jin, H., Wong, M.-L., & Leung, K.-S. (2005). Scalable model-based clustering for large databases based on data summarization. IEEE Transactions on Pattern Analysis & Machine Intelligence, 27(11), 1710-1719. doi: 10.1109/TPAMI.2005.226

Share

COinS