KNAC : an approach for enhancing cluster analysis with background knowledge and explanations

2023
journal article
article
3
dc.abstract.enPattern discovery in multidimensional data sets has been the subject of research for decades. There exists a wide spectrum of clustering algorithms that can be used for this purpose. However, their practical applications share a common post-clustering phase, which concerns expert-based interpretation and analysis of the obtained results. We argue that this can be the bottleneck in the process, especially in cases where domain knowledge exists prior to clustering. Such a situation requires not only a proper analysis of automatically discovered clusters but also conformance checking with existing knowledge. In this work, we present Knowledge Augmented Clustering (KNAC). Its main goal is to confront expert-based labelling with automated clustering for the sake of updating and refining the former. Our solution is not restricted to any existing clustering algorithm. Instead, KNAC can serve as an augmentation of an arbitrary clustering algorithm, making the approach robust and a model-agnostic improvement of any state-of-the-art clustering method. We demonstrate the feasibility of our method on artificially, reproducible examples and in a real life use case scenario. In both cases, we achieved better results than classic clustering algorithms without augmentation.pl
dc.affiliationWydział Fizyki, Astronomii i Informatyki Stosowanej : Instytut Informatyki Stosowanejpl
dc.contributor.authorBobek, Szymon - 428058 pl
dc.contributor.authorKuk, Michałpl
dc.contributor.authorBrzegowski, Jakubpl
dc.contributor.authorBrzychczy, Edytapl
dc.contributor.authorNalepa, Grzegorz - 200414 pl
dc.date.accessioned2023-05-15T14:10:37Z
dc.date.available2023-05-15T14:10:37Z
dc.date.issued2023pl
dc.date.openaccess0
dc.description.accesstimew momencie opublikowania
dc.description.additionalOnline First 2022-11-23pl
dc.description.number12pl
dc.description.physical15537-15560pl
dc.description.versionostateczna wersja wydawcy
dc.description.volume53pl
dc.identifier.doi10.1007/s10489-022-04310-9pl
dc.identifier.eissn1573-7497pl
dc.identifier.issn0924-669Xpl
dc.identifier.projectNCN 2018/27/Z/ST6/03392pl
dc.identifier.projectU1U/P06/NO/02.16pl
dc.identifier.urihttps://ruj.uj.edu.pl/xmlui/handle/item/311349
dc.languageengpl
dc.language.containerengpl
dc.pbn.affiliationDziedzina nauk inżynieryjno-technicznych : informatyka techniczna i telekomunikacjapl
dc.rightsUdzielam licencji. Uznanie autorstwa 4.0 Międzynarodowa*
dc.rights.licenceCC-BY
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/legalcode.pl*
dc.share.typeinne
dc.subject.endata miningpl
dc.subject.enexplainable AIpl
dc.subject.enclusteringpl
dc.subtypeArticlepl
dc.titleKNAC : an approach for enhancing cluster analysis with background knowledge and explanationspl
dc.title.journalApplied Intelligencepl
dc.typeJournalArticlepl
dspace.entity.typePublication
dc.abstract.enpl
Pattern discovery in multidimensional data sets has been the subject of research for decades. There exists a wide spectrum of clustering algorithms that can be used for this purpose. However, their practical applications share a common post-clustering phase, which concerns expert-based interpretation and analysis of the obtained results. We argue that this can be the bottleneck in the process, especially in cases where domain knowledge exists prior to clustering. Such a situation requires not only a proper analysis of automatically discovered clusters but also conformance checking with existing knowledge. In this work, we present Knowledge Augmented Clustering (KNAC). Its main goal is to confront expert-based labelling with automated clustering for the sake of updating and refining the former. Our solution is not restricted to any existing clustering algorithm. Instead, KNAC can serve as an augmentation of an arbitrary clustering algorithm, making the approach robust and a model-agnostic improvement of any state-of-the-art clustering method. We demonstrate the feasibility of our method on artificially, reproducible examples and in a real life use case scenario. In both cases, we achieved better results than classic clustering algorithms without augmentation.
dc.affiliationpl
Wydział Fizyki, Astronomii i Informatyki Stosowanej : Instytut Informatyki Stosowanej
dc.contributor.authorpl
Bobek, Szymon - 428058
dc.contributor.authorpl
Kuk, Michał
dc.contributor.authorpl
Brzegowski, Jakub
dc.contributor.authorpl
Brzychczy, Edyta
dc.contributor.authorpl
Nalepa, Grzegorz - 200414
dc.date.accessioned
2023-05-15T14:10:37Z
dc.date.available
2023-05-15T14:10:37Z
dc.date.issuedpl
2023
dc.date.openaccess
0
dc.description.accesstime
w momencie opublikowania
dc.description.additionalpl
Online First 2022-11-23
dc.description.numberpl
12
dc.description.physicalpl
15537-15560
dc.description.version
ostateczna wersja wydawcy
dc.description.volumepl
53
dc.identifier.doipl
10.1007/s10489-022-04310-9
dc.identifier.eissnpl
1573-7497
dc.identifier.issnpl
0924-669X
dc.identifier.projectpl
NCN 2018/27/Z/ST6/03392
dc.identifier.projectpl
U1U/P06/NO/02.16
dc.identifier.uri
https://ruj.uj.edu.pl/xmlui/handle/item/311349
dc.languagepl
eng
dc.language.containerpl
eng
dc.pbn.affiliationpl
Dziedzina nauk inżynieryjno-technicznych : informatyka techniczna i telekomunikacja
dc.rights*
Udzielam licencji. Uznanie autorstwa 4.0 Międzynarodowa
dc.rights.licence
CC-BY
dc.rights.uri*
http://creativecommons.org/licenses/by/4.0/legalcode.pl
dc.share.type
inne
dc.subject.enpl
data mining
dc.subject.enpl
explainable AI
dc.subject.enpl
clustering
dc.subtypepl
Article
dc.titlepl
KNAC : an approach for enhancing cluster analysis with background knowledge and explanations
dc.title.journalpl
Applied Intelligence
dc.typepl
JournalArticle
dspace.entity.type
Publication
Affiliations

* The migration of download and view statistics prior to the date of April 8, 2024 is in progress.

Views
3
Views per month
Views per city
Warsaw
2
Mogilany
1
Downloads
bobek_brzegowski_nalepa_et-al_knac_an_approach_for_enhancing_cluster_analysis_2023.pdf
11