No Cover Image

Conference Paper/Proceeding/Abstract 201 views 5 downloads

Active Deep Clustering: Exploratory Analysis to Assist in Decision-Making on Incremental Label Morphing Datasets

Connor Clarkson, Mike Edwards Orcid Logo, Xianghua Xie Orcid Logo

ACIVS 2025 / LNCS

Swansea University Authors: Connor Clarkson, Mike Edwards Orcid Logo, Xianghua Xie Orcid Logo

  • ACIVS_ADC_Exploratory_Analysis_to_Assist_in_Decision_Making_on_Incremental_Label_Morphing_Datasets.pdf

    PDF | Accepted Manuscript

    Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).

    Download (1.53MB)

Abstract

Many supervised-based training schemes rely on the need to have a single associated label for each data sample within a set. Where the goal is to learn different levels of granularity of the data in an implicit form, in the context of neural networks, this is accomplished with different layers to ex...

Full description

Published in: ACIVS 2025 / LNCS
Published:
URI: https://cronfa.swan.ac.uk/Record/cronfa70372
first_indexed 2025-09-17T11:06:25Z
last_indexed 2025-11-14T12:46:27Z
id cronfa70372
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-11-13T15:42:10.1563564</datestamp><bib-version>v2</bib-version><id>70372</id><entry>2025-09-17</entry><title>Active Deep Clustering: Exploratory Analysis to Assist in Decision-Making on Incremental Label Morphing Datasets</title><swanseaauthors><author><sid>e1a00716a3866cd4d8bb0ade1bada119</sid><firstname>Connor</firstname><surname>Clarkson</surname><name>Connor Clarkson</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>684864a1ce01c3d774e83ed55e41770e</sid><ORCID>0000-0003-3367-969X</ORCID><firstname>Mike</firstname><surname>Edwards</surname><name>Mike Edwards</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-09-17</date><deptcode>MACS</deptcode><abstract>Many supervised-based training schemes rely on the need to have a single associated label for each data sample within a set. Where the goal is to learn different levels of granularity of the data in an implicit form, in the context of neural networks, this is accomplished with different layers to extract features at distinct levels. In this work, we explore more explicit labelling structures where each sample has multiple labels forming relationships at both an abstract and fine-grained level, producing a tree for each associated data sample. This novel type of training scheme utilises a refinement strategy based on deep clustering approaches to detect the colliding and splitting of clusters where each is assigned a label. Experts can then be queried to determine if those colliding clusters should belong to a single label, or alternatively, if they are splitting, should we create new labels, forming an active component of our training scheme. Colliding clusters form a parent label while splitting clusters form sibling labels within the tree structure. By utilizing a tree data structure to represent labels at different levels of granularity, we can invoke explicitly defined relationships and dependencies to form a more structured and interpretable representation of data. Instead of treating data as flat, homogenous sets, we allow for the exploitation of hierarchical relationships and leverage inherent structure to improve data efficiency. We present a case study of the approach applied within the steel manufacturing domain, where quality control remains an active challenge due to morphing labels as products move down the production line.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>ACIVS 2025 / LNCS</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords/><publishedDay>0</publishedDay><publishedMonth>0</publishedMonth><publishedYear>0</publishedYear><publishedDate>0001-01-01</publishedDate><doi/><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2025-11-13T15:42:10.1563564</lastEdited><Created>2025-09-17T11:55:46.2153113</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>Connor</firstname><surname>Clarkson</surname><order>1</order></author><author><firstname>Mike</firstname><surname>Edwards</surname><orcid>0000-0003-3367-969X</orcid><order>2</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>3</order></author></authors><documents><document><filename>70372__35100__859e7120214042928f71c1612b3f822f.pdf</filename><originalFilename>ACIVS_ADC_Exploratory_Analysis_to_Assist_in_Decision_Making_on_Incremental_Label_Morphing_Datasets.pdf</originalFilename><uploaded>2025-09-17T12:04:47.3399516</uploaded><type>Output</type><contentLength>1605122</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2025-11-24T00:00:00.0000000</embargoDate><documentNotes>Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/deed.en</licence></document></documents><OutputDurs/></rfc1807>
spelling 2025-11-13T15:42:10.1563564 v2 70372 2025-09-17 Active Deep Clustering: Exploratory Analysis to Assist in Decision-Making on Incremental Label Morphing Datasets e1a00716a3866cd4d8bb0ade1bada119 Connor Clarkson Connor Clarkson true false 684864a1ce01c3d774e83ed55e41770e 0000-0003-3367-969X Mike Edwards Mike Edwards true false b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2025-09-17 MACS Many supervised-based training schemes rely on the need to have a single associated label for each data sample within a set. Where the goal is to learn different levels of granularity of the data in an implicit form, in the context of neural networks, this is accomplished with different layers to extract features at distinct levels. In this work, we explore more explicit labelling structures where each sample has multiple labels forming relationships at both an abstract and fine-grained level, producing a tree for each associated data sample. This novel type of training scheme utilises a refinement strategy based on deep clustering approaches to detect the colliding and splitting of clusters where each is assigned a label. Experts can then be queried to determine if those colliding clusters should belong to a single label, or alternatively, if they are splitting, should we create new labels, forming an active component of our training scheme. Colliding clusters form a parent label while splitting clusters form sibling labels within the tree structure. By utilizing a tree data structure to represent labels at different levels of granularity, we can invoke explicitly defined relationships and dependencies to form a more structured and interpretable representation of data. Instead of treating data as flat, homogenous sets, we allow for the exploitation of hierarchical relationships and leverage inherent structure to improve data efficiency. We present a case study of the approach applied within the steel manufacturing domain, where quality control remains an active challenge due to morphing labels as products move down the production line. Conference Paper/Proceeding/Abstract ACIVS 2025 / LNCS 0 0 0 0001-01-01 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University 2025-11-13T15:42:10.1563564 2025-09-17T11:55:46.2153113 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Connor Clarkson 1 Mike Edwards 0000-0003-3367-969X 2 Xianghua Xie 0000-0002-2701-8660 3 70372__35100__859e7120214042928f71c1612b3f822f.pdf ACIVS_ADC_Exploratory_Analysis_to_Assist_in_Decision_Making_on_Incremental_Label_Morphing_Datasets.pdf 2025-09-17T12:04:47.3399516 Output 1605122 application/pdf Accepted Manuscript true 2025-11-24T00:00:00.0000000 Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention). true eng https://creativecommons.org/licenses/by/4.0/deed.en
title Active Deep Clustering: Exploratory Analysis to Assist in Decision-Making on Incremental Label Morphing Datasets
spellingShingle Active Deep Clustering: Exploratory Analysis to Assist in Decision-Making on Incremental Label Morphing Datasets
Connor Clarkson
Mike Edwards
Xianghua Xie
title_short Active Deep Clustering: Exploratory Analysis to Assist in Decision-Making on Incremental Label Morphing Datasets
title_full Active Deep Clustering: Exploratory Analysis to Assist in Decision-Making on Incremental Label Morphing Datasets
title_fullStr Active Deep Clustering: Exploratory Analysis to Assist in Decision-Making on Incremental Label Morphing Datasets
title_full_unstemmed Active Deep Clustering: Exploratory Analysis to Assist in Decision-Making on Incremental Label Morphing Datasets
title_sort Active Deep Clustering: Exploratory Analysis to Assist in Decision-Making on Incremental Label Morphing Datasets
author_id_str_mv e1a00716a3866cd4d8bb0ade1bada119
684864a1ce01c3d774e83ed55e41770e
b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv e1a00716a3866cd4d8bb0ade1bada119_***_Connor Clarkson
684864a1ce01c3d774e83ed55e41770e_***_Mike Edwards
b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie
author Connor Clarkson
Mike Edwards
Xianghua Xie
author2 Connor Clarkson
Mike Edwards
Xianghua Xie
format Conference Paper/Proceeding/Abstract
container_title ACIVS 2025 / LNCS
institution Swansea University
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 Many supervised-based training schemes rely on the need to have a single associated label for each data sample within a set. Where the goal is to learn different levels of granularity of the data in an implicit form, in the context of neural networks, this is accomplished with different layers to extract features at distinct levels. In this work, we explore more explicit labelling structures where each sample has multiple labels forming relationships at both an abstract and fine-grained level, producing a tree for each associated data sample. This novel type of training scheme utilises a refinement strategy based on deep clustering approaches to detect the colliding and splitting of clusters where each is assigned a label. Experts can then be queried to determine if those colliding clusters should belong to a single label, or alternatively, if they are splitting, should we create new labels, forming an active component of our training scheme. Colliding clusters form a parent label while splitting clusters form sibling labels within the tree structure. By utilizing a tree data structure to represent labels at different levels of granularity, we can invoke explicitly defined relationships and dependencies to form a more structured and interpretable representation of data. Instead of treating data as flat, homogenous sets, we allow for the exploitation of hierarchical relationships and leverage inherent structure to improve data efficiency. We present a case study of the approach applied within the steel manufacturing domain, where quality control remains an active challenge due to morphing labels as products move down the production line.
published_date 0001-01-01T05:30:41Z
_version_ 1851098023299383296
score 11.089386

Similar Items