Efficient subspace clustering of large-scale data streams with misses

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

As the amount of data generated and communicated continuously increases, clustering algorithms that are not able to handle this enormous amount of data have to be redesigned. Recent subspace clustering advances, while powerful, are computationally and memory demanding. The present paper introduces an online algorithm that broadens high-performance batch subspace clustering methods, and is able to perform subspace clustering on data arriving sequentially and possibly with misses. Numerical tests on synthetic and real data demonstrate the potential of the proposed approach.

Original languageEnglish (US)
Title of host publication2016 50th Annual Conference on Information Systems and Sciences, CISS 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages590-595
Number of pages6
ISBN (Electronic)9781467394574
DOIs
StatePublished - Apr 26 2016
Event50th Annual Conference on Information Systems and Sciences, CISS 2016 - Princeton, United States
Duration: Mar 16 2016Mar 18 2016

Publication series

Name2016 50th Annual Conference on Information Systems and Sciences, CISS 2016

Other

Other50th Annual Conference on Information Systems and Sciences, CISS 2016
CountryUnited States
CityPrinceton
Period3/16/163/18/16

Bibliographical note

Funding Information:
Work was supported by NSF grants 1500713, 1514056; ARO W911NF-15-1-0492; and NIH 1R01GM104975-01.

Keywords

  • Low-rank representation
  • Missing entries
  • Online
  • Streaming
  • Subspace clustering

Fingerprint Dive into the research topics of 'Efficient subspace clustering of large-scale data streams with misses'. Together they form a unique fingerprint.

Cite this