Least-squares community extraction in feature-rich networks using similarity data.

We explore a doubly-greedy approach to the issue of community detection in feature-rich networks. According to this approach, both the network and feature data are straightforwardly recovered from the underlying unknown non-overlapping communities, supplied with a center in the feature space and int...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Soroosh Shalileh, Boris Mirkin
Formato: article
Lenguaje:EN
Publicado: Public Library of Science (PLoS) 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/d93a00a917b64d39a6a3f6d18cadbc80
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:d93a00a917b64d39a6a3f6d18cadbc80
record_format dspace
spelling oai:doaj.org-article:d93a00a917b64d39a6a3f6d18cadbc802021-12-02T20:09:14ZLeast-squares community extraction in feature-rich networks using similarity data.1932-620310.1371/journal.pone.0254377https://doaj.org/article/d93a00a917b64d39a6a3f6d18cadbc802021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0254377https://doaj.org/toc/1932-6203We explore a doubly-greedy approach to the issue of community detection in feature-rich networks. According to this approach, both the network and feature data are straightforwardly recovered from the underlying unknown non-overlapping communities, supplied with a center in the feature space and intensity weight(s) over the network each. Our least-squares additive criterion allows us to search for communities one-by-one and to find each community by adding entities one by one. A focus of this paper is that the feature-space data part is converted into a similarity matrix format. The similarity/link values can be used in either of two modes: (a) as measured in the same scale so that one may can meaningfully compare and sum similarity values across the entire similarity matrix (summability mode), and (b) similarity values in one column should not be compared with the values in other columns (nonsummability mode). The two input matrices and two modes lead us to developing four different Iterative Community Extraction from Similarity data (ICESi) algorithms, which determine the number of communities automatically. Our experiments at real-world and synthetic datasets show that these algorithms are valid and competitive.Soroosh ShalilehBoris MirkinPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 7, p e0254377 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Soroosh Shalileh
Boris Mirkin
Least-squares community extraction in feature-rich networks using similarity data.
description We explore a doubly-greedy approach to the issue of community detection in feature-rich networks. According to this approach, both the network and feature data are straightforwardly recovered from the underlying unknown non-overlapping communities, supplied with a center in the feature space and intensity weight(s) over the network each. Our least-squares additive criterion allows us to search for communities one-by-one and to find each community by adding entities one by one. A focus of this paper is that the feature-space data part is converted into a similarity matrix format. The similarity/link values can be used in either of two modes: (a) as measured in the same scale so that one may can meaningfully compare and sum similarity values across the entire similarity matrix (summability mode), and (b) similarity values in one column should not be compared with the values in other columns (nonsummability mode). The two input matrices and two modes lead us to developing four different Iterative Community Extraction from Similarity data (ICESi) algorithms, which determine the number of communities automatically. Our experiments at real-world and synthetic datasets show that these algorithms are valid and competitive.
format article
author Soroosh Shalileh
Boris Mirkin
author_facet Soroosh Shalileh
Boris Mirkin
author_sort Soroosh Shalileh
title Least-squares community extraction in feature-rich networks using similarity data.
title_short Least-squares community extraction in feature-rich networks using similarity data.
title_full Least-squares community extraction in feature-rich networks using similarity data.
title_fullStr Least-squares community extraction in feature-rich networks using similarity data.
title_full_unstemmed Least-squares community extraction in feature-rich networks using similarity data.
title_sort least-squares community extraction in feature-rich networks using similarity data.
publisher Public Library of Science (PLoS)
publishDate 2021
url https://doaj.org/article/d93a00a917b64d39a6a3f6d18cadbc80
work_keys_str_mv AT sorooshshalileh leastsquarescommunityextractioninfeaturerichnetworksusingsimilaritydata
AT borismirkin leastsquarescommunityextractioninfeaturerichnetworksusingsimilaritydata
_version_ 1718375153434361856