SHrimp: descriptive patterns in a tree

Sibylle Hess; Nico Piatkowski; Katharina Morik

SHrimp: descriptive patterns in a tree

Sibylle Hess, Nico Piatkowski, Katharina Morik

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

2 Citations (Scopus)

23 Downloads (Pure)

Abstract

The appliance of the minimum description length (MDL) principle to the field of theory mining enables a precise description of main characteristics of a dataset in comparison to the numerous and hardly understandable output of the popular frequent pattern mining algorithms. The loss function that determines the quality of a pattern selection with respect to the MDL principle is however difficult to analyze and the selection is computed heuristically for all known algorithms. With SHrimp, the attempt to create a data structure that re ects the influences of the pattern selection to the database and that enables a faster computation of the quality of the selection is initiated.

Original language	English
Title of host publication	LWA 2014 Workshops KDML, IR and FGWM
Subtitle of host publication	Proceedings of the 16th LWA Workshops: KDML, IR and FGWM Aachen, Germany, September 8-10, 2014.
Editors	Thomas Seidl, Marwan Hassani, Christian Beecks
Publisher	CEUR-WS.org
Pages	181-192
Number of pages	12
Publication status	Published - 10 Sept 2014
Externally published	Yes
Event	16th Workshops on Learning, Knowledge, Adaptation, LWA 2014: Knowledge Discovery, Data Mining and Machine Learning, KDML 2014, Information Retrieval, IR 2014 and Knowledge Management, FGWM 2014 - Aachen, Germany Duration: 8 Sept 2014 → 10 Sept 2014 http://ceur-ws.org/Vol-1226/ (link to proceedings)

Publication series

Name	CEUR Workshop Proceedings
Number	1226
ISSN (Print)	1613-0073

Conference

Conference	16th Workshops on Learning, Knowledge, Adaptation, LWA 2014: Knowledge Discovery, Data Mining and Machine Learning, KDML 2014, Information Retrieval, IR 2014 and Knowledge Management, FGWM 2014
Country/Territory	Germany
City	Aachen
Period	8/09/14 → 10/09/14
Internet address	http://ceur-ws.org/Vol-1226/ (link to proceedings)

Keywords

Itemsets
MDL
Pattern mining
Pattern selection

Access to Document

published versionFinal published version, 1.4 MB

Cite this

@inproceedings{4183baa68da1499492388313c2a8e453,

title = "SHrimp: descriptive patterns in a tree",

abstract = "The appliance of the minimum description length (MDL) principle to the field of theory mining enables a precise description of main characteristics of a dataset in comparison to the numerous and hardly understandable output of the popular frequent pattern mining algorithms. The loss function that determines the quality of a pattern selection with respect to the MDL principle is however difficult to analyze and the selection is computed heuristically for all known algorithms. With SHrimp, the attempt to create a data structure that re ects the influences of the pattern selection to the database and that enables a faster computation of the quality of the selection is initiated.",

keywords = "Itemsets, MDL, Pattern mining, Pattern selection",

author = "Sibylle Hess and Nico Piatkowski and Katharina Morik",

year = "2014",

month = sep,

day = "10",

language = "English",

series = "CEUR Workshop Proceedings",

publisher = "CEUR-WS.org",

number = "1226",

pages = "181--192",

editor = "Seidl, {Thomas } and Marwan Hassani and Christian Beecks",

booktitle = "LWA 2014 Workshops KDML, IR and FGWM",

note = "16th Workshops on Learning, Knowledge, Adaptation, LWA 2014: Knowledge Discovery, Data Mining and Machine Learning, KDML 2014, Information Retrieval, IR 2014 and Knowledge Management, FGWM 2014 ; Conference date: 08-09-2014 Through 10-09-2014",

url = "http://ceur-ws.org/Vol-1226/",

}

Hess, S, Piatkowski, N & Morik, K 2014, SHrimp: descriptive patterns in a tree. in T Seidl, M Hassani & C Beecks (eds), LWA 2014 Workshops KDML, IR and FGWM: Proceedings of the 16th LWA Workshops: KDML, IR and FGWM Aachen, Germany, September 8-10, 2014.. CEUR Workshop Proceedings, no. 1226, CEUR-WS.org, pp. 181-192, 16th Workshops on Learning, Knowledge, Adaptation, LWA 2014: Knowledge Discovery, Data Mining and Machine Learning, KDML 2014, Information Retrieval, IR 2014 and Knowledge Management, FGWM 2014, Aachen, Germany, 8/09/14.

SHrimp: descriptive patterns in a tree. / Hess, Sibylle; Piatkowski, Nico; Morik, Katharina.
LWA 2014 Workshops KDML, IR and FGWM: Proceedings of the 16th LWA Workshops: KDML, IR and FGWM Aachen, Germany, September 8-10, 2014.. ed. / Thomas Seidl; Marwan Hassani; Christian Beecks. CEUR-WS.org, 2014. p. 181-192 (CEUR Workshop Proceedings; No. 1226).

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

TY - GEN

T1 - SHrimp

T2 - 16th Workshops on Learning, Knowledge, Adaptation, LWA 2014: Knowledge Discovery, Data Mining and Machine Learning, KDML 2014, Information Retrieval, IR 2014 and Knowledge Management, FGWM 2014

AU - Hess, Sibylle

AU - Piatkowski, Nico

AU - Morik, Katharina

PY - 2014/9/10

Y1 - 2014/9/10

N2 - The appliance of the minimum description length (MDL) principle to the field of theory mining enables a precise description of main characteristics of a dataset in comparison to the numerous and hardly understandable output of the popular frequent pattern mining algorithms. The loss function that determines the quality of a pattern selection with respect to the MDL principle is however difficult to analyze and the selection is computed heuristically for all known algorithms. With SHrimp, the attempt to create a data structure that re ects the influences of the pattern selection to the database and that enables a faster computation of the quality of the selection is initiated.

AB - The appliance of the minimum description length (MDL) principle to the field of theory mining enables a precise description of main characteristics of a dataset in comparison to the numerous and hardly understandable output of the popular frequent pattern mining algorithms. The loss function that determines the quality of a pattern selection with respect to the MDL principle is however difficult to analyze and the selection is computed heuristically for all known algorithms. With SHrimp, the attempt to create a data structure that re ects the influences of the pattern selection to the database and that enables a faster computation of the quality of the selection is initiated.

KW - Itemsets

KW - MDL

KW - Pattern mining

KW - Pattern selection

UR - http://www.scopus.com/inward/record.url?scp=84924999991&partnerID=8YFLogxK

UR - http://ceur-ws.org/Vol-1226/

M3 - Conference contribution

AN - SCOPUS:84924999991

T3 - CEUR Workshop Proceedings

SP - 181

EP - 192

BT - LWA 2014 Workshops KDML, IR and FGWM

A2 - Seidl, Thomas

A2 - Hassani, Marwan

A2 - Beecks, Christian

PB - CEUR-WS.org

Y2 - 8 September 2014 through 10 September 2014

ER -

SHrimp: descriptive patterns in a tree

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this