Mining Local Staircase Patterns in Noisy Data

Thanh Le Van; Ana Carolina Fierro; Mattias Guns; Matthijs van Leeuwen; Siegfried Nijssen; Luc De Raedt; Kathleen Marchal

doi:10.1109/ICDMW.2012.83

Mining Local Staircase Patterns in Noisy Data

Thanh Le Van, Ana Carolina Fierro, Mattias Guns, Matthijs van Leeuwen, Siegfried Nijssen, Luc De Raedt, Kathleen Marchal

Business technology and Operations

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › Research

Abstract

Most traditional biclustering algorithms identify biclusters with no or little overlap. In this paper, we introduce the problem of identifying staircases of biclusters. Such staircases may be indicative for causal relationships between columns and can not easily be identified by existing biclustering algorithms. Our formalization relies on a scoring function based on the Minimum Description Length principle. Furthermore, we propose a first algorithm for identifying staircase biclusters, based on a combination of local search and constraint programming. Experiments show that the approach is promising.

Original language	English
Title of host publication	12th IEEE International Conference on Data Mining Workshops, ICDM Workshops, Brussels, Belgium, December 10, 2012
Editors	Jilles Vreeken, Charles Ling, Mohamed Javeed Zaki, Arno Siebes, Jeffrey Xu Yu, Bart Goethals, Geoffrey I. Webb, Xindong Wu
Publisher	IEEE Computer Society
Pages	139-146
DOIs	https://doi.org/10.1109/ICDMW.2012.83
Publication status	Published - 2012
Event	ICDM 2012: IEEE International Conference on Data Mining - Brussels, Belgium Duration: 10 Dec 2012 → 10 Dec 2012

Conference

Conference	ICDM 2012
Abbreviated title	ICDM 2012
Country/Territory	Belgium
City	Brussels
Period	10/12/12 → 10/12/12

Access to Document

10.1109/ICDMW.2012.83

Cite this

Le Van, T., Fierro, A. C., Guns, M., van Leeuwen, M., Nijssen, S., De Raedt, L., & Marchal, K. (2012). Mining Local Staircase Patterns in Noisy Data. In J. Vreeken, C. Ling, M. J. Zaki, A. Siebes, J. X. Yu, B. Goethals, G. I. Webb, & X. Wu (Eds.), 12th IEEE International Conference on Data Mining Workshops, ICDM Workshops, Brussels, Belgium, December 10, 2012 (pp. 139-146). IEEE Computer Society. https://doi.org/10.1109/ICDMW.2012.83

Le Van, Thanh ; Fierro, Ana Carolina ; Guns, Mattias ; van Leeuwen, Matthijs ; Nijssen, Siegfried ; De Raedt, Luc ; Marchal, Kathleen. / Mining Local Staircase Patterns in Noisy Data. 12th IEEE International Conference on Data Mining Workshops, ICDM Workshops, Brussels, Belgium, December 10, 2012. editor / Jilles Vreeken ; Charles Ling ; Mohamed Javeed Zaki ; Arno Siebes ; Jeffrey Xu Yu ; Bart Goethals ; Geoffrey I. Webb ; Xindong Wu. IEEE Computer Society, 2012. pp. 139-146

@inproceedings{ddbcf50b85b645b8bfd50fc06f9a0f83,

title = "Mining Local Staircase Patterns in Noisy Data",

abstract = "Most traditional biclustering algorithms identify biclusters with no or little overlap. In this paper, we introduce the problem of identifying staircases of biclusters. Such staircases may be indicative for causal relationships between columns and can not easily be identified by existing biclustering algorithms. Our formalization relies on a scoring function based on the Minimum Description Length principle. Furthermore, we propose a first algorithm for identifying staircase biclusters, based on a combination of local search and constraint programming. Experiments show that the approach is promising.",

author = "{Le Van}, Thanh and Fierro, {Ana Carolina} and Mattias Guns and {van Leeuwen}, Matthijs and Siegfried Nijssen and {De Raedt}, Luc and Kathleen Marchal",

year = "2012",

doi = "10.1109/ICDMW.2012.83",

language = "English",

pages = "139--146",

editor = "Jilles Vreeken and Charles Ling and Zaki, {Mohamed Javeed} and Arno Siebes and Yu, {Jeffrey Xu} and Bart Goethals and Webb, {Geoffrey I.} and Xindong Wu",

booktitle = "12th IEEE International Conference on Data Mining Workshops, ICDM Workshops, Brussels, Belgium, December 10, 2012",

publisher = "IEEE Computer Society",

address = "United States",

note = "ICDM 2012 : IEEE International Conference on Data Mining , ICDM 2012 ; Conference date: 10-12-2012 Through 10-12-2012",

}

Le Van, T, Fierro, AC, Guns, M, van Leeuwen, M, Nijssen, S, De Raedt, L & Marchal, K 2012, Mining Local Staircase Patterns in Noisy Data. in J Vreeken, C Ling, MJ Zaki, A Siebes, JX Yu, B Goethals, GI Webb & X Wu (eds), 12th IEEE International Conference on Data Mining Workshops, ICDM Workshops, Brussels, Belgium, December 10, 2012. IEEE Computer Society, pp. 139-146, ICDM 2012, Brussels, Belgium, 10/12/12. https://doi.org/10.1109/ICDMW.2012.83

Mining Local Staircase Patterns in Noisy Data. / Le Van, Thanh; Fierro, Ana Carolina; Guns, Mattias; van Leeuwen, Matthijs; Nijssen, Siegfried; De Raedt, Luc; Marchal, Kathleen.

12th IEEE International Conference on Data Mining Workshops, ICDM Workshops, Brussels, Belgium, December 10, 2012. ed. / Jilles Vreeken; Charles Ling; Mohamed Javeed Zaki; Arno Siebes; Jeffrey Xu Yu; Bart Goethals; Geoffrey I. Webb; Xindong Wu. IEEE Computer Society, 2012. p. 139-146.

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › Research

TY - GEN

T1 - Mining Local Staircase Patterns in Noisy Data

AU - Le Van, Thanh

AU - Fierro, Ana Carolina

AU - Guns, Mattias

AU - van Leeuwen, Matthijs

AU - Nijssen, Siegfried

AU - De Raedt, Luc

AU - Marchal, Kathleen

PY - 2012

Y1 - 2012

N2 - Most traditional biclustering algorithms identify biclusters with no or little overlap. In this paper, we introduce the problem of identifying staircases of biclusters. Such staircases may be indicative for causal relationships between columns and can not easily be identified by existing biclustering algorithms. Our formalization relies on a scoring function based on the Minimum Description Length principle. Furthermore, we propose a first algorithm for identifying staircase biclusters, based on a combination of local search and constraint programming. Experiments show that the approach is promising.

AB - Most traditional biclustering algorithms identify biclusters with no or little overlap. In this paper, we introduce the problem of identifying staircases of biclusters. Such staircases may be indicative for causal relationships between columns and can not easily be identified by existing biclustering algorithms. Our formalization relies on a scoring function based on the Minimum Description Length principle. Furthermore, we propose a first algorithm for identifying staircase biclusters, based on a combination of local search and constraint programming. Experiments show that the approach is promising.

U2 - 10.1109/ICDMW.2012.83

DO - 10.1109/ICDMW.2012.83

M3 - Conference paper

SP - 139

EP - 146

BT - 12th IEEE International Conference on Data Mining Workshops, ICDM Workshops, Brussels, Belgium, December 10, 2012

A2 - Vreeken, Jilles

A2 - Ling, Charles

A2 - Zaki, Mohamed Javeed

A2 - Siebes, Arno

A2 - Yu, Jeffrey Xu

A2 - Goethals, Bart

A2 - Webb, Geoffrey I.

A2 - Wu, Xindong

PB - IEEE Computer Society

T2 - ICDM 2012

Y2 - 10 December 2012 through 10 December 2012

ER -

Le Van T, Fierro AC, Guns M, van Leeuwen M, Nijssen S, De Raedt L et al. Mining Local Staircase Patterns in Noisy Data. In Vreeken J, Ling C, Zaki MJ, Siebes A, Yu JX, Goethals B, Webb GI, Wu X, editors, 12th IEEE International Conference on Data Mining Workshops, ICDM Workshops, Brussels, Belgium, December 10, 2012. IEEE Computer Society. 2012. p. 139-146 https://doi.org/10.1109/ICDMW.2012.83

Mining Local Staircase Patterns in Noisy Data

Abstract

Conference

Access to Document

Fingerprint

Cite this