Orthogonal decision trees

Hillol Kargupta; Haimonti Dutta

doi:10.1109/ICDM.2004.10072

Orthogonal decision trees

Hillol Kargupta
, Haimonti Dutta

Management Science and Systems

University of Maryland, Baltimore County
AGNIK, LLC

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Scopus citations

Abstract

This paper introduces orthogonal decision trees that offer an effective way to construct a redundancy-free, accurate, and meaningful representation of large decision-tree-ensembles often created by popular techniques such as Bagging, Boosting, Random Forests and many distributed and data stream mining algorithms. Orthogonal decision trees are functionally orthogonal to each other and they correspond to the principal components of the underlying function space. This paper offers a technique to construct such trees based on eigen-analysis of the ensemble and offers experimental results to document the performance of orthogonal trees on grounds of accuracy and model complexity.

Original language	English
Title of host publication	Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004
Editors	R. Rastogi, K. Morik, M. Bramer, X. Wu
Pages	427-430
Number of pages	4
DOIs	https://doi.org/10.1109/ICDM.2004.10072
State	Published - 2004
Event	Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004 - Brighton, United Kingdom Duration: Nov 1 2004 → Nov 4 2004

Publication series

Name	Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004

Conference

Conference	Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004
Country/Territory	United Kingdom
City	Brighton
Period	11/1/04 → 11/4/04

Access to Document

10.1109/ICDM.2004.10072

Cite this

@inproceedings{3296d66185a6451a913cac2c2fcf7672,

title = "Orthogonal decision trees",

abstract = "This paper introduces orthogonal decision trees that offer an effective way to construct a redundancy-free, accurate, and meaningful representation of large decision-tree-ensembles often created by popular techniques such as Bagging, Boosting, Random Forests and many distributed and data stream mining algorithms. Orthogonal decision trees are functionally orthogonal to each other and they correspond to the principal components of the underlying function space. This paper offers a technique to construct such trees based on eigen-analysis of the ensemble and offers experimental results to document the performance of orthogonal trees on grounds of accuracy and model complexity.",

author = "Hillol Kargupta and Haimonti Dutta",

year = "2004",

doi = "10.1109/ICDM.2004.10072",

language = "English",

isbn = "0769521428",

series = "Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004",

pages = "427--430",

editor = "R. Rastogi and K. Morik and M. Bramer and X. Wu",

booktitle = "Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004",

note = "Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004 ; Conference date: 01-11-2004 Through 04-11-2004",

}

Kargupta, H & Dutta, H 2004, Orthogonal decision trees. in R Rastogi, K Morik, M Bramer & X Wu (eds), Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004. Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004, pp. 427-430, Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004, Brighton, United Kingdom, 11/1/04. https://doi.org/10.1109/ICDM.2004.10072

Orthogonal decision trees. / Kargupta, Hillol; Dutta, Haimonti.
Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004. ed. / R. Rastogi; K. Morik; M. Bramer; X. Wu. 2004. p. 427-430 (Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Orthogonal decision trees

AU - Kargupta, Hillol

AU - Dutta, Haimonti

PY - 2004

Y1 - 2004

N2 - This paper introduces orthogonal decision trees that offer an effective way to construct a redundancy-free, accurate, and meaningful representation of large decision-tree-ensembles often created by popular techniques such as Bagging, Boosting, Random Forests and many distributed and data stream mining algorithms. Orthogonal decision trees are functionally orthogonal to each other and they correspond to the principal components of the underlying function space. This paper offers a technique to construct such trees based on eigen-analysis of the ensemble and offers experimental results to document the performance of orthogonal trees on grounds of accuracy and model complexity.

AB - This paper introduces orthogonal decision trees that offer an effective way to construct a redundancy-free, accurate, and meaningful representation of large decision-tree-ensembles often created by popular techniques such as Bagging, Boosting, Random Forests and many distributed and data stream mining algorithms. Orthogonal decision trees are functionally orthogonal to each other and they correspond to the principal components of the underlying function space. This paper offers a technique to construct such trees based on eigen-analysis of the ensemble and offers experimental results to document the performance of orthogonal trees on grounds of accuracy and model complexity.

UR - https://www.scopus.com/pages/publications/19544371912

U2 - 10.1109/ICDM.2004.10072

DO - 10.1109/ICDM.2004.10072

M3 - Conference contribution

AN - SCOPUS:19544371912

SN - 0769521428

SN - 9780769521428

T3 - Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004

SP - 427

EP - 430

BT - Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004

A2 - Rastogi, R.

A2 - Morik, K.

A2 - Bramer, M.

A2 - Wu, X.

T2 - Proceedings - Fourth IEEE International Conference on Data Mining, ICDM 2004

Y2 - 1 November 2004 through 4 November 2004

ER -

Orthogonal decision trees

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this