No Cover Image

Journal article 477 views 76 downloads

Towards explainable community finding

Sophie Sadler, Derek Greene, Daniel Archambault Orcid Logo

Applied Network Science, Volume: 7, Issue: 1

Swansea University Authors: Sophie Sadler, Daniel Archambault Orcid Logo

  • 62122.VOR.pdf

    PDF | Version of Record

    Distributed under the terms of a Creative Commons 4.0 Attribution Licence. Copyright, The Authors.

    Download (3.13MB)

Check full text

DOI (Published version): 10.1007/s41109-022-00515-6

Abstract

The detection of communities of nodes is an important task in understanding the structure of networks. Multiple approaches have been developed to tackle this problem, many of which are in common usage in real-world applications, such as in public health networks. However, clear insight into the reas...

Full description

Published in: Applied Network Science
ISSN: 2364-8228
Published: Springer Science and Business Media LLC 2022
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa62122
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2022-12-05T15:17:10Z
last_indexed 2023-01-13T19:23:22Z
id cronfa62122
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2023-01-09T12:12:20.8351181</datestamp><bib-version>v2</bib-version><id>62122</id><entry>2022-12-05</entry><title>Towards explainable community finding</title><swanseaauthors><author><sid>780d416ff624ef8e4541830674bfac0e</sid><firstname>Sophie</firstname><surname>Sadler</surname><name>Sophie Sadler</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>8fa6987716a22304ef04d3c3d50ef266</sid><ORCID>0000-0003-4978-8479</ORCID><firstname>Daniel</firstname><surname>Archambault</surname><name>Daniel Archambault</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2022-12-05</date><deptcode>SMA</deptcode><abstract>The detection of communities of nodes is an important task in understanding the structure of networks. Multiple approaches have been developed to tackle this problem, many of which are in common usage in real-world applications, such as in public health networks. However, clear insight into the reasoning behind the community labels produced by these algorithms is rarely provided. Drawing inspiration from the machine learning literature, we aim to provide post-hoc explanations for the outputs of these algorithms using interpretable features of the network. In this paper, we propose a model-agnostic methodology that identifies a set of informative features to help explain the output of a community finding algorithm. We apply it to three well-known algorithms, though the methodology is designed to generalise to new approaches. As well as identifying important features for a post-hoc explanation system, we report on the common features found made by the different algorithms and the differences between the approaches.</abstract><type>Journal Article</type><journal>Applied Network Science</journal><volume>7</volume><journalNumber>1</journalNumber><paginationStart/><paginationEnd/><publisher>Springer Science and Business Media LLC</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2364-8228</issnElectronic><keywords>Network Analysis; Graph Mining; Community Detection; Explainability</keywords><publishedDay>8</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2022</publishedYear><publishedDate>2022-12-08</publishedDate><doi>10.1007/s41109-022-00515-6</doi><url/><notes/><college>COLLEGE NANME</college><department>Mathematics</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SMA</DepartmentCode><institution>Swansea University</institution><apcterm>External research funder(s) paid the OA fee (includes OA grants disbursed by the Library)</apcterm><funders>This work is supported by the UKRI AIMLAC CDT, funded by Grant EP/S023992/1 and by the UKRI EPSRC Grant EP/V033670/1. The research was also partly supported by Science Foundation Ireland (SFI) under Grant No. SFI/12/RC/2289_P2.</funders><projectreference/><lastEdited>2023-01-09T12:12:20.8351181</lastEdited><Created>2022-12-05T15:09:44.4814926</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Sophie</firstname><surname>Sadler</surname><order>1</order></author><author><firstname>Derek</firstname><surname>Greene</surname><order>2</order></author><author><firstname>Daniel</firstname><surname>Archambault</surname><orcid>0000-0003-4978-8479</orcid><order>3</order></author></authors><documents><document><filename>62122__26056__f602cad4d8fa4c1db4a5f5433c8c83a0.pdf</filename><originalFilename>62122.VOR.pdf</originalFilename><uploaded>2022-12-12T09:05:52.8312800</uploaded><type>Output</type><contentLength>3279586</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>Distributed under the terms of a Creative Commons 4.0 Attribution Licence. Copyright, The Authors.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2023-01-09T12:12:20.8351181 v2 62122 2022-12-05 Towards explainable community finding 780d416ff624ef8e4541830674bfac0e Sophie Sadler Sophie Sadler true false 8fa6987716a22304ef04d3c3d50ef266 0000-0003-4978-8479 Daniel Archambault Daniel Archambault true false 2022-12-05 SMA The detection of communities of nodes is an important task in understanding the structure of networks. Multiple approaches have been developed to tackle this problem, many of which are in common usage in real-world applications, such as in public health networks. However, clear insight into the reasoning behind the community labels produced by these algorithms is rarely provided. Drawing inspiration from the machine learning literature, we aim to provide post-hoc explanations for the outputs of these algorithms using interpretable features of the network. In this paper, we propose a model-agnostic methodology that identifies a set of informative features to help explain the output of a community finding algorithm. We apply it to three well-known algorithms, though the methodology is designed to generalise to new approaches. As well as identifying important features for a post-hoc explanation system, we report on the common features found made by the different algorithms and the differences between the approaches. Journal Article Applied Network Science 7 1 Springer Science and Business Media LLC 2364-8228 Network Analysis; Graph Mining; Community Detection; Explainability 8 12 2022 2022-12-08 10.1007/s41109-022-00515-6 COLLEGE NANME Mathematics COLLEGE CODE SMA Swansea University External research funder(s) paid the OA fee (includes OA grants disbursed by the Library) This work is supported by the UKRI AIMLAC CDT, funded by Grant EP/S023992/1 and by the UKRI EPSRC Grant EP/V033670/1. The research was also partly supported by Science Foundation Ireland (SFI) under Grant No. SFI/12/RC/2289_P2. 2023-01-09T12:12:20.8351181 2022-12-05T15:09:44.4814926 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Sophie Sadler 1 Derek Greene 2 Daniel Archambault 0000-0003-4978-8479 3 62122__26056__f602cad4d8fa4c1db4a5f5433c8c83a0.pdf 62122.VOR.pdf 2022-12-12T09:05:52.8312800 Output 3279586 application/pdf Version of Record true Distributed under the terms of a Creative Commons 4.0 Attribution Licence. Copyright, The Authors. true eng http://creativecommons.org/licenses/by/4.0/
title Towards explainable community finding
spellingShingle Towards explainable community finding
Sophie Sadler
Daniel Archambault
title_short Towards explainable community finding
title_full Towards explainable community finding
title_fullStr Towards explainable community finding
title_full_unstemmed Towards explainable community finding
title_sort Towards explainable community finding
author_id_str_mv 780d416ff624ef8e4541830674bfac0e
8fa6987716a22304ef04d3c3d50ef266
author_id_fullname_str_mv 780d416ff624ef8e4541830674bfac0e_***_Sophie Sadler
8fa6987716a22304ef04d3c3d50ef266_***_Daniel Archambault
author Sophie Sadler
Daniel Archambault
author2 Sophie Sadler
Derek Greene
Daniel Archambault
format Journal article
container_title Applied Network Science
container_volume 7
container_issue 1
publishDate 2022
institution Swansea University
issn 2364-8228
doi_str_mv 10.1007/s41109-022-00515-6
publisher Springer Science and Business Media LLC
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description The detection of communities of nodes is an important task in understanding the structure of networks. Multiple approaches have been developed to tackle this problem, many of which are in common usage in real-world applications, such as in public health networks. However, clear insight into the reasoning behind the community labels produced by these algorithms is rarely provided. Drawing inspiration from the machine learning literature, we aim to provide post-hoc explanations for the outputs of these algorithms using interpretable features of the network. In this paper, we propose a model-agnostic methodology that identifies a set of informative features to help explain the output of a community finding algorithm. We apply it to three well-known algorithms, though the methodology is designed to generalise to new approaches. As well as identifying important features for a post-hoc explanation system, we report on the common features found made by the different algorithms and the differences between the approaches.
published_date 2022-12-08T04:21:30Z
_version_ 1763754419387629568
score 11.035874

Similar Items