Target unbiased meta-learning for graph classification

Li, Ming; Zhu, Shuo; Li, Chunxu; Zhao, Wencang

doi:10.1093/jcde/qwab050

Journal article 227 views 43 downloads

Target unbiased meta-learning for graph classification

Ming Li, Shuo Zhu, Chunxu Li

, Wencang Zhao

Journal of Computational Design and Engineering, Volume: 8, Issue: 5, Pages: 1355 - 1366

Swansea University Author: Chunxu Li

PDF | Version of Record

Copyright: The Author(s) 2021. . This is an Open Access article distributed under the terms of the Creative Commons Attribution License.
Download (4.73MB)

Check full text

DOI (Published version): 10.1093/jcde/qwab050

Abstract

Even though numerous works focus on the few-shot learning issue by combining meta-learning, there are still limits to traditional graph classification problems. The antecedent algorithms directly extract features from the samples, and do not take into account the preference of the trained model to t...

Full description

Published in:	Journal of Computational Design and Engineering
ISSN:	2288-5048
Published:	Oxford University Press (OUP) 2021
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa66004
Tags:	Add Tag No Tags, Be the first to tag this record!

first_indexed	2024-04-10T08:25:18Z
last_indexed	2024-04-10T08:25:18Z
id	cronfa66004
recordtype	SURis
fullrecord	<?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>66004</id><entry>2024-04-09</entry><title>Target unbiased meta-learning for graph classification</title><swanseaauthors><author><sid>e6ed70d02c25b05ab52340312559d684</sid><ORCID>0000-0001-7851-0260</ORCID><firstname>Chunxu</firstname><surname>Li</surname><name>Chunxu Li</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2024-04-09</date><deptcode>ACEM</deptcode><abstract>Even though numerous works focus on the few-shot learning issue by combining meta-learning, there are still limits to traditional graph classification problems. The antecedent algorithms directly extract features from the samples, and do not take into account the preference of the trained model to the previously “seen” targets. In order to overcome the aforementioned issues, an effective strategy with training an unbiased meta-learning algorithm was developed in this paper, which sorted out problems of target preference and few-shot under the meta-learning paradigm. First, the interactive attention extraction module as a supplement to feature extraction was employed, which improved the separability of feature vectors, reduced the preference of the model for a certain target, and remarkably improved the generalization ability of the model on the new task. Second, the graph neural network was used to fully mine the relationship between samples to constitute graph structures and complete image classification tasks at a node level, which greatly enhanced the accuracy of classification. A series of experimental studies were conducted to validate the proposed methodology, where the few-shot and semisupervised learning problem has been effectively solved. It also proved that our model has better accuracy than traditional classification methods on real-world datasets.</abstract><type>Journal Article</type><journal>Journal of Computational Design and Engineering</journal><volume>8</volume><journalNumber>5</journalNumber><paginationStart>1355</paginationStart><paginationEnd>1366</paginationEnd><publisher>Oxford University Press (OUP)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2288-5048</issnElectronic><keywords>meta-learning, graph neural networks, graph classification, few-shot learning</keywords><publishedDay>15</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-09-15</publishedDate><doi>10.1093/jcde/qwab050</doi><url/><notes/><college>COLLEGE NANME</college><department>Aerospace, Civil, Electrical, and Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>ACEM</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders/><projectreference/><lastEdited>2024-05-22T16:00:02.8804822</lastEdited><Created>2024-04-09T20:07:59.3101911</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering</level></path><authors><author><firstname>Ming</firstname><surname>Li</surname><order>1</order></author><author><firstname>Shuo</firstname><surname>Zhu</surname><order>2</order></author><author><firstname>Chunxu</firstname><surname>Li</surname><orcid>0000-0001-7851-0260</orcid><order>3</order></author><author><firstname>Wencang</firstname><surname>Zhao</surname><order>4</order></author></authors><documents><document><filename>66004__30442__dc59602128aa42e3b01f4622bedde5d9.pdf</filename><originalFilename>66004.VoR.pdf</originalFilename><uploaded>2024-05-22T15:58:04.5877836</uploaded><type>Output</type><contentLength>4955275</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright: The Author(s) 2021. . This is an Open Access article distributed under the terms of the Creative Commons Attribution License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	v2 66004 2024-04-09 Target unbiased meta-learning for graph classification e6ed70d02c25b05ab52340312559d684 0000-0001-7851-0260 Chunxu Li Chunxu Li true false 2024-04-09 ACEM Even though numerous works focus on the few-shot learning issue by combining meta-learning, there are still limits to traditional graph classification problems. The antecedent algorithms directly extract features from the samples, and do not take into account the preference of the trained model to the previously “seen” targets. In order to overcome the aforementioned issues, an effective strategy with training an unbiased meta-learning algorithm was developed in this paper, which sorted out problems of target preference and few-shot under the meta-learning paradigm. First, the interactive attention extraction module as a supplement to feature extraction was employed, which improved the separability of feature vectors, reduced the preference of the model for a certain target, and remarkably improved the generalization ability of the model on the new task. Second, the graph neural network was used to fully mine the relationship between samples to constitute graph structures and complete image classification tasks at a node level, which greatly enhanced the accuracy of classification. A series of experimental studies were conducted to validate the proposed methodology, where the few-shot and semisupervised learning problem has been effectively solved. It also proved that our model has better accuracy than traditional classification methods on real-world datasets. Journal Article Journal of Computational Design and Engineering 8 5 1355 1366 Oxford University Press (OUP) 2288-5048 meta-learning, graph neural networks, graph classification, few-shot learning 15 9 2021 2021-09-15 10.1093/jcde/qwab050 COLLEGE NANME Aerospace, Civil, Electrical, and Mechanical Engineering COLLEGE CODE ACEM Swansea University Another institution paid the OA fee 2024-05-22T16:00:02.8804822 2024-04-09T20:07:59.3101911 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering Ming Li 1 Shuo Zhu 2 Chunxu Li 0000-0001-7851-0260 3 Wencang Zhao 4 66004__30442__dc59602128aa42e3b01f4622bedde5d9.pdf 66004.VoR.pdf 2024-05-22T15:58:04.5877836 Output 4955275 application/pdf Version of Record true Copyright: The Author(s) 2021. . This is an Open Access article distributed under the terms of the Creative Commons Attribution License. true eng http://creativecommons.org/licenses/by/4.0/
title	Target unbiased meta-learning for graph classification
spellingShingle	Target unbiased meta-learning for graph classification Chunxu Li
title_short	Target unbiased meta-learning for graph classification
title_full	Target unbiased meta-learning for graph classification
title_fullStr	Target unbiased meta-learning for graph classification
title_full_unstemmed	Target unbiased meta-learning for graph classification
title_sort	Target unbiased meta-learning for graph classification
author_id_str_mv	e6ed70d02c25b05ab52340312559d684
author_id_fullname_str_mv	e6ed70d02c25b05ab52340312559d684_***_Chunxu Li
author	Chunxu Li
author2	Ming Li Shuo Zhu Chunxu Li Wencang Zhao
format	Journal article
container_title	Journal of Computational Design and Engineering
container_volume	8
container_issue	5
container_start_page	1355
publishDate	2021
institution	Swansea University
issn	2288-5048
doi_str_mv	10.1093/jcde/qwab050
publisher	Oxford University Press (OUP)
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 Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering
document_store_str	1
active_str	0
description	Even though numerous works focus on the few-shot learning issue by combining meta-learning, there are still limits to traditional graph classification problems. The antecedent algorithms directly extract features from the samples, and do not take into account the preference of the trained model to the previously “seen” targets. In order to overcome the aforementioned issues, an effective strategy with training an unbiased meta-learning algorithm was developed in this paper, which sorted out problems of target preference and few-shot under the meta-learning paradigm. First, the interactive attention extraction module as a supplement to feature extraction was employed, which improved the separability of feature vectors, reduced the preference of the model for a certain target, and remarkably improved the generalization ability of the model on the new task. Second, the graph neural network was used to fully mine the relationship between samples to constitute graph structures and complete image classification tasks at a node level, which greatly enhanced the accuracy of classification. A series of experimental studies were conducted to validate the proposed methodology, where the few-shot and semisupervised learning problem has been effectively solved. It also proved that our model has better accuracy than traditional classification methods on real-world datasets.
published_date	2021-09-15T16:00:01Z
_version_	1799765361856348160
score	11.037603

Target unbiased meta-learning for graph classification

Similar Items