An Unsupervised Boosting Strategy for Outlier Detection Ensembles

Guilherme Oliveira Campos, Arthur Zimek, Wagner Meira Jr.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Ensemble techniques have been applied to the unsupervised outlier detection problem in some scenarios. Challenges are the generation of diverse ensemble members and the combination of individual results into an ensemble. For the latter challenge, some methods tried to design smaller ensembles out of a wealth of possible ensemble members, to improve the diversity and accuracy of the ensemble (relating to the ensemble selection problem in classification). We propose a boosting strategy for combinations showing improvements on benchmark datasets.
Original languageEnglish
Title of host publicationAdvances in Knowledge Discovery and Data Mining : Proceedings, Part I
EditorsDinh Phung, Vincent S. Tseng, Geoffrey I. Webb, Bao Ho, Mohadeseh Ganji, Lida Rashidi
Volume10937
PublisherSpringer
Publication date2018
Pages564-576
ISBN (Print)978-3-319-93033-6
ISBN (Electronic)978-3-319-93034-3
DOIs
Publication statusPublished - 2018
EventPacific-Asia Conference on Knowledge Discovery and Data Mining - Melbourne, Australia
Duration: 3 Jun 20186 Jun 2018
Conference number: 22
http://prada-research.net/pakdd18/

Conference

ConferencePacific-Asia Conference on Knowledge Discovery and Data Mining
Number22
CountryAustralia
CityMelbourne
Period03/06/201806/06/2018
Internet address
SeriesLecture Notes in Computer Science
Volume10937
ISSN0302-9743
SeriesLecture Notes in Artificial Intelligence
Volume10937

Fingerprint

outlier
detection
method

Keywords

  • Outlier detection
  • Ensembles
  • Boosting
  • Ensemble selection

Cite this

Campos, G. O., Zimek, A., & Meira Jr., W. (2018). An Unsupervised Boosting Strategy for Outlier Detection Ensembles. In D. Phung, V. S. Tseng, G. I. Webb, B. Ho, M. Ganji, & L. Rashidi (Eds.), Advances in Knowledge Discovery and Data Mining: Proceedings, Part I (Vol. 10937, pp. 564-576). Springer. Lecture Notes in Computer Science, Vol.. 10937, Lecture Notes in Artificial Intelligence, Vol.. 10937 https://doi.org/10.1007/978-3-319-93034-3_45
Campos, Guilherme Oliveira ; Zimek, Arthur ; Meira Jr., Wagner. / An Unsupervised Boosting Strategy for Outlier Detection Ensembles. Advances in Knowledge Discovery and Data Mining: Proceedings, Part I. editor / Dinh Phung ; Vincent S. Tseng ; Geoffrey I. Webb ; Bao Ho ; Mohadeseh Ganji ; Lida Rashidi. Vol. 10937 Springer, 2018. pp. 564-576 (Lecture Notes in Computer Science, Vol. 10937). (Lecture Notes in Artificial Intelligence, Vol. 10937).
@inproceedings{b22523e21397450fb1cf37c6f60ee072,
title = "An Unsupervised Boosting Strategy for Outlier Detection Ensembles",
abstract = "Ensemble techniques have been applied to the unsupervised outlier detection problem in some scenarios. Challenges are the generation of diverse ensemble members and the combination of individual results into an ensemble. For the latter challenge, some methods tried to design smaller ensembles out of a wealth of possible ensemble members, to improve the diversity and accuracy of the ensemble (relating to the ensemble selection problem in classification). We propose a boosting strategy for combinations showing improvements on benchmark datasets.",
keywords = "Outlier detection, Ensembles, Boosting, Ensemble selection",
author = "Campos, {Guilherme Oliveira} and Arthur Zimek and {Meira Jr.}, Wagner",
year = "2018",
doi = "10.1007/978-3-319-93034-3_45",
language = "English",
isbn = "978-3-319-93033-6",
volume = "10937",
pages = "564--576",
editor = "Dinh Phung and {S. Tseng}, Vincent and {I. Webb}, Geoffrey and Bao Ho and Mohadeseh Ganji and Lida Rashidi",
booktitle = "Advances in Knowledge Discovery and Data Mining",
publisher = "Springer",
address = "Germany",

}

Campos, GO, Zimek, A & Meira Jr., W 2018, An Unsupervised Boosting Strategy for Outlier Detection Ensembles. in D Phung, V S. Tseng, G I. Webb, B Ho, M Ganji & L Rashidi (eds), Advances in Knowledge Discovery and Data Mining: Proceedings, Part I. vol. 10937, Springer, Lecture Notes in Computer Science, vol. 10937, Lecture Notes in Artificial Intelligence, vol. 10937, pp. 564-576, Pacific-Asia Conference on Knowledge Discovery and Data Mining, Melbourne, Australia, 03/06/2018. https://doi.org/10.1007/978-3-319-93034-3_45

An Unsupervised Boosting Strategy for Outlier Detection Ensembles. / Campos, Guilherme Oliveira; Zimek, Arthur; Meira Jr., Wagner.

Advances in Knowledge Discovery and Data Mining: Proceedings, Part I. ed. / Dinh Phung; Vincent S. Tseng; Geoffrey I. Webb; Bao Ho; Mohadeseh Ganji; Lida Rashidi. Vol. 10937 Springer, 2018. p. 564-576.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - An Unsupervised Boosting Strategy for Outlier Detection Ensembles

AU - Campos, Guilherme Oliveira

AU - Zimek, Arthur

AU - Meira Jr., Wagner

PY - 2018

Y1 - 2018

N2 - Ensemble techniques have been applied to the unsupervised outlier detection problem in some scenarios. Challenges are the generation of diverse ensemble members and the combination of individual results into an ensemble. For the latter challenge, some methods tried to design smaller ensembles out of a wealth of possible ensemble members, to improve the diversity and accuracy of the ensemble (relating to the ensemble selection problem in classification). We propose a boosting strategy for combinations showing improvements on benchmark datasets.

AB - Ensemble techniques have been applied to the unsupervised outlier detection problem in some scenarios. Challenges are the generation of diverse ensemble members and the combination of individual results into an ensemble. For the latter challenge, some methods tried to design smaller ensembles out of a wealth of possible ensemble members, to improve the diversity and accuracy of the ensemble (relating to the ensemble selection problem in classification). We propose a boosting strategy for combinations showing improvements on benchmark datasets.

KW - Outlier detection

KW - Ensembles

KW - Boosting

KW - Ensemble selection

U2 - 10.1007/978-3-319-93034-3_45

DO - 10.1007/978-3-319-93034-3_45

M3 - Article in proceedings

SN - 978-3-319-93033-6

VL - 10937

SP - 564

EP - 576

BT - Advances in Knowledge Discovery and Data Mining

A2 - Phung, Dinh

A2 - S. Tseng, Vincent

A2 - I. Webb, Geoffrey

A2 - Ho, Bao

A2 - Ganji, Mohadeseh

A2 - Rashidi, Lida

PB - Springer

ER -

Campos GO, Zimek A, Meira Jr. W. An Unsupervised Boosting Strategy for Outlier Detection Ensembles. In Phung D, S. Tseng V, I. Webb G, Ho B, Ganji M, Rashidi L, editors, Advances in Knowledge Discovery and Data Mining: Proceedings, Part I. Vol. 10937. Springer. 2018. p. 564-576. (Lecture Notes in Computer Science, Vol. 10937). (Lecture Notes in Artificial Intelligence, Vol. 10937). https://doi.org/10.1007/978-3-319-93034-3_45