Multi-relational Community Detection in Social Platforms Using Graph Neural Networks

Nouamane Arhachoui; Vincent Gauthier; Anastasios Giovanidis; Lionel Tabourier

doi:10.1007/978-3-032-00206-8_11

Multi-relational Community Detection in Social Platforms Using Graph Neural Networks

Nouamane Arhachoui
, Vincent Gauthier
, Anastasios Giovanidis
, Lionel Tabourier

Sorbonne Université

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

Abstract

We propose a method to detect communities in multi-relational networks, based on a graph neural network pipeline. The method allows to target areas where communities are consensual over the different modes of the network, which are processed as different networks in the pipeline. This is done by combining the outcomes of multiple simple Graph Neural Networks, applied on each of the graphs representing different forms of interactions between users of the social platform. The method is validated on a synthetic benchmark, as a first step for further improvements. In particular, the flexible architecture of the pipeline allows to swap its subparts and create variants of community detection.

Original language	English
Title of host publication	Studies in Systems, Decision and Control
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	112-123
Number of pages	12
DOIs	https://doi.org/10.1007/978-3-032-00206-8_11
Publication status	Published - 1 Jan 2025

Publication series

Name	Studies in Systems, Decision and Control
Volume	615
ISSN (Print)	2198-4182
ISSN (Electronic)	2198-4190

Keywords

community detection
graph neural networks
multi-relational networks
online social platforms

Access to Document

10.1007/978-3-032-00206-8_11

Cite this

@inbook{dc54ae2a678347208506e41178904db7,

title = "Multi-relational Community Detection in Social Platforms Using Graph Neural Networks",

abstract = "We propose a method to detect communities in multi-relational networks, based on a graph neural network pipeline. The method allows to target areas where communities are consensual over the different modes of the network, which are processed as different networks in the pipeline. This is done by combining the outcomes of multiple simple Graph Neural Networks, applied on each of the graphs representing different forms of interactions between users of the social platform. The method is validated on a synthetic benchmark, as a first step for further improvements. In particular, the flexible architecture of the pipeline allows to swap its subparts and create variants of community detection.",

keywords = "community detection, graph neural networks, multi-relational networks, online social platforms",

author = "Nouamane Arhachoui and Vincent Gauthier and Anastasios Giovanidis and Lionel Tabourier",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.",

year = "2025",

month = jan,

day = "1",

doi = "10.1007/978-3-032-00206-8\_11",

language = "English",

series = "Studies in Systems, Decision and Control",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "112--123",

booktitle = "Studies in Systems, Decision and Control",

}

Multi-relational Community Detection in Social Platforms Using Graph Neural Networks. / Arhachoui, Nouamane; Gauthier, Vincent; Giovanidis, Anastasios et al.
Studies in Systems, Decision and Control. Springer Science and Business Media Deutschland GmbH, 2025. p. 112-123 (Studies in Systems, Decision and Control; Vol. 615).

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

TY - CHAP

T1 - Multi-relational Community Detection in Social Platforms Using Graph Neural Networks

AU - Arhachoui, Nouamane

AU - Gauthier, Vincent

AU - Giovanidis, Anastasios

AU - Tabourier, Lionel

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

PY - 2025/1/1

Y1 - 2025/1/1

N2 - We propose a method to detect communities in multi-relational networks, based on a graph neural network pipeline. The method allows to target areas where communities are consensual over the different modes of the network, which are processed as different networks in the pipeline. This is done by combining the outcomes of multiple simple Graph Neural Networks, applied on each of the graphs representing different forms of interactions between users of the social platform. The method is validated on a synthetic benchmark, as a first step for further improvements. In particular, the flexible architecture of the pipeline allows to swap its subparts and create variants of community detection.

AB - We propose a method to detect communities in multi-relational networks, based on a graph neural network pipeline. The method allows to target areas where communities are consensual over the different modes of the network, which are processed as different networks in the pipeline. This is done by combining the outcomes of multiple simple Graph Neural Networks, applied on each of the graphs representing different forms of interactions between users of the social platform. The method is validated on a synthetic benchmark, as a first step for further improvements. In particular, the flexible architecture of the pipeline allows to swap its subparts and create variants of community detection.

KW - community detection

KW - graph neural networks

KW - multi-relational networks

KW - online social platforms

UR - https://www.scopus.com/pages/publications/105017927701

U2 - 10.1007/978-3-032-00206-8_11

DO - 10.1007/978-3-032-00206-8_11

M3 - Chapter

AN - SCOPUS:105017927701

T3 - Studies in Systems, Decision and Control

SP - 112

EP - 123

BT - Studies in Systems, Decision and Control

PB - Springer Science and Business Media Deutschland GmbH

ER -