Spectral estimation for detecting low-dimensional structure in networks using arbitrary null models.

Discovering low-dimensional structure in real-world networks requires a suitable null model that defines the absence of meaningful structure. Here we introduce a spectral approach for detecting a network's low-dimensional structure, and the nodes that participate in it, using any null model. We...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Mark D Humphries, Javier A Caballero, Mat Evans, Silvia Maggi, Abhinav Singh
Formato: article
Lenguaje:EN
Publicado: Public Library of Science (PLoS) 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/8e3af9a39a9346388a00ba72b8347795
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:8e3af9a39a9346388a00ba72b8347795
record_format dspace
spelling oai:doaj.org-article:8e3af9a39a9346388a00ba72b83477952021-12-02T20:09:41ZSpectral estimation for detecting low-dimensional structure in networks using arbitrary null models.1932-620310.1371/journal.pone.0254057https://doaj.org/article/8e3af9a39a9346388a00ba72b83477952021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0254057https://doaj.org/toc/1932-6203Discovering low-dimensional structure in real-world networks requires a suitable null model that defines the absence of meaningful structure. Here we introduce a spectral approach for detecting a network's low-dimensional structure, and the nodes that participate in it, using any null model. We use generative models to estimate the expected eigenvalue distribution under a specified null model, and then detect where the data network's eigenspectra exceed the estimated bounds. On synthetic networks, this spectral estimation approach cleanly detects transitions between random and community structure, recovers the number and membership of communities, and removes noise nodes. On real networks spectral estimation finds either a significant fraction of noise nodes or no departure from a null model, in stark contrast to traditional community detection methods. Across all analyses, we find the choice of null model can strongly alter conclusions about the presence of network structure. Our spectral estimation approach is therefore a promising basis for detecting low-dimensional structure in real-world networks, or lack thereof.Mark D HumphriesJavier A CaballeroMat EvansSilvia MaggiAbhinav SinghPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 7, p e0254057 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Mark D Humphries
Javier A Caballero
Mat Evans
Silvia Maggi
Abhinav Singh
Spectral estimation for detecting low-dimensional structure in networks using arbitrary null models.
description Discovering low-dimensional structure in real-world networks requires a suitable null model that defines the absence of meaningful structure. Here we introduce a spectral approach for detecting a network's low-dimensional structure, and the nodes that participate in it, using any null model. We use generative models to estimate the expected eigenvalue distribution under a specified null model, and then detect where the data network's eigenspectra exceed the estimated bounds. On synthetic networks, this spectral estimation approach cleanly detects transitions between random and community structure, recovers the number and membership of communities, and removes noise nodes. On real networks spectral estimation finds either a significant fraction of noise nodes or no departure from a null model, in stark contrast to traditional community detection methods. Across all analyses, we find the choice of null model can strongly alter conclusions about the presence of network structure. Our spectral estimation approach is therefore a promising basis for detecting low-dimensional structure in real-world networks, or lack thereof.
format article
author Mark D Humphries
Javier A Caballero
Mat Evans
Silvia Maggi
Abhinav Singh
author_facet Mark D Humphries
Javier A Caballero
Mat Evans
Silvia Maggi
Abhinav Singh
author_sort Mark D Humphries
title Spectral estimation for detecting low-dimensional structure in networks using arbitrary null models.
title_short Spectral estimation for detecting low-dimensional structure in networks using arbitrary null models.
title_full Spectral estimation for detecting low-dimensional structure in networks using arbitrary null models.
title_fullStr Spectral estimation for detecting low-dimensional structure in networks using arbitrary null models.
title_full_unstemmed Spectral estimation for detecting low-dimensional structure in networks using arbitrary null models.
title_sort spectral estimation for detecting low-dimensional structure in networks using arbitrary null models.
publisher Public Library of Science (PLoS)
publishDate 2021
url https://doaj.org/article/8e3af9a39a9346388a00ba72b8347795
work_keys_str_mv AT markdhumphries spectralestimationfordetectinglowdimensionalstructureinnetworksusingarbitrarynullmodels
AT javieracaballero spectralestimationfordetectinglowdimensionalstructureinnetworksusingarbitrarynullmodels
AT matevans spectralestimationfordetectinglowdimensionalstructureinnetworksusingarbitrarynullmodels
AT silviamaggi spectralestimationfordetectinglowdimensionalstructureinnetworksusingarbitrarynullmodels
AT abhinavsingh spectralestimationfordetectinglowdimensionalstructureinnetworksusingarbitrarynullmodels
_version_ 1718375074465054720