RankMerging: Apprentissage supervisé de classements pour la prédiction de liens dans les grands réseaux sociaux

Lionel Tabourier; Anne-Sophie Libert; Renaud Lambiotte

RankMerging: Apprentissage supervisé de classements pour la prédiction de liens dans les grands réseaux sociaux

Translated title of the contribution: RankMerging: A supervised learning-to-rank for predicting links in large-scale social networks

Lionel Tabourier, Anne-Sophie Libert, Renaud Lambiotte

Namur Institute for Complex Systems

Research output: Contribution in Book/Catalog/Report/Conference proceeding › Conference contribution

Abstract

Uncovering missing links in social networks is a difficult task because of their sparsity, and because links may represent different types of relationships, characterized by different structural patterns. In this paper, we define a simple supervised learning-to-rank framework, called RankMerging, which aims at combining information provided by various unsupervised rankings. As an illustration, we apply the method to the case of a cell phone service provider, which aims at discovering links among contractors of its competitors. We show that our method substantially improves the performance of the available classification methods.

Translated title of the contribution	RankMerging: A supervised learning-to-rank for predicting links in large-scale social networks
Original language	French
Title of host publication	Extraction et Gestion des Connaissances, EGC 2015
Publisher	Cambridge University Press
Pages	395-400
Number of pages	6
Volume	E.28
ISBN (Electronic)	9782705690229
Publication status	Published - 1 Jan 2015
Event	Quinzieme Conference Internationale Francophone sur l'Extraction et la Gestion des Connaissances, EGC 2015 - 15th International French-Speaking Conference on Knowledge Extraction and Management, EGC 2015 - Luxembourg, Luxembourg Duration: 27 Jan 2015 → 30 Jan 2015

Conference

Conference	Quinzieme Conference Internationale Francophone sur l'Extraction et la Gestion des Connaissances, EGC 2015 - 15th International French-Speaking Conference on Knowledge Extraction and Management, EGC 2015
Country/Territory	Luxembourg
City	Luxembourg
Period	27/01/15 → 30/01/15

Cite this

@inproceedings{23625a97baa24527a5f4198f5186c63b,

title = "RankMerging: Apprentissage supervis{\'e} de classements pour la pr{\'e}diction de liens dans les grands r{\'e}seaux sociaux",

abstract = "Uncovering missing links in social networks is a difficult task because of their sparsity, and because links may represent different types of relationships, characterized by different structural patterns. In this paper, we define a simple supervised learning-to-rank framework, called RankMerging, which aims at combining information provided by various unsupervised rankings. As an illustration, we apply the method to the case of a cell phone service provider, which aims at discovering links among contractors of its competitors. We show that our method substantially improves the performance of the available classification methods.",

author = "Lionel Tabourier and Anne-Sophie Libert and Renaud Lambiotte",

year = "2015",

month = jan,

day = "1",

language = "Fran{\c c}ais",

volume = "E.28",

pages = "395--400",

booktitle = "Extraction et Gestion des Connaissances, EGC 2015",

publisher = "Cambridge University Press",

note = "Quinzieme Conference Internationale Francophone sur l'Extraction et la Gestion des Connaissances, EGC 2015 - 15th International French-Speaking Conference on Knowledge Extraction and Management, EGC 2015 ; Conference date: 27-01-2015 Through 30-01-2015",

}

Tabourier, L, Libert, A-S & Lambiotte, R 2015, RankMerging: Apprentissage supervisé de classements pour la prédiction de liens dans les grands réseaux sociaux. in Extraction et Gestion des Connaissances, EGC 2015. vol. E.28, Cambridge University Press, pp. 395-400, Quinzieme Conference Internationale Francophone sur l'Extraction et la Gestion des Connaissances, EGC 2015 - 15th International French-Speaking Conference on Knowledge Extraction and Management, EGC 2015, Luxembourg, Luxembourg, 27/01/15.

RankMerging: Apprentissage supervisé de classements pour la prédiction de liens dans les grands réseaux sociaux. / Tabourier, Lionel; Libert, Anne-Sophie ; Lambiotte, Renaud.
Extraction et Gestion des Connaissances, EGC 2015. Vol. E.28 Cambridge University Press, 2015. p. 395-400.

Research output: Contribution in Book/Catalog/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - RankMerging

T2 - Quinzieme Conference Internationale Francophone sur l'Extraction et la Gestion des Connaissances, EGC 2015 - 15th International French-Speaking Conference on Knowledge Extraction and Management, EGC 2015

AU - Tabourier, Lionel

AU - Libert, Anne-Sophie

AU - Lambiotte, Renaud

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Uncovering missing links in social networks is a difficult task because of their sparsity, and because links may represent different types of relationships, characterized by different structural patterns. In this paper, we define a simple supervised learning-to-rank framework, called RankMerging, which aims at combining information provided by various unsupervised rankings. As an illustration, we apply the method to the case of a cell phone service provider, which aims at discovering links among contractors of its competitors. We show that our method substantially improves the performance of the available classification methods.

AB - Uncovering missing links in social networks is a difficult task because of their sparsity, and because links may represent different types of relationships, characterized by different structural patterns. In this paper, we define a simple supervised learning-to-rank framework, called RankMerging, which aims at combining information provided by various unsupervised rankings. As an illustration, we apply the method to the case of a cell phone service provider, which aims at discovering links among contractors of its competitors. We show that our method substantially improves the performance of the available classification methods.

UR - http://www.scopus.com/inward/record.url?scp=84994589435&partnerID=8YFLogxK

M3 - Article dans les actes d'une conférence/un colloque

AN - SCOPUS:84994589435

VL - E.28

SP - 395

EP - 400

BT - Extraction et Gestion des Connaissances, EGC 2015

PB - Cambridge University Press

Y2 - 27 January 2015 through 30 January 2015

ER -

RankMerging: Apprentissage supervisé de classements pour la prédiction de liens dans les grands réseaux sociaux

Abstract

Conference

Other files and links

Fingerprint

Cite this