Meta-MOGA: Meta-learning Multi-Objective Genetic Algorithm

In the field of single objective optimization algorithms, learned evolutionary algorithms have achieved success in obtaining better performance than human-designed strategies. However, these learnable evolutionary algorithms are only applicable to single-objective optimization and cannot be applied...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2025 IEEE Congress on Evolutionary Computation (CEC) s. 1 - 4
Hlavní autori: Li, Tianyu, Wu, Kai, Li, Xiaobin, Teng, Xiangyi, Liu, Jing
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 08.06.2025
Predmet:
Evolutionary computation
Evolutionary multi-objective optimization algorithms
Genetic algorithms
Meta-learning
Metalearning
Multi-objective optimization
Multilayer perceptrons
Optimization
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract In the field of single objective optimization algorithms, learned evolutionary algorithms have achieved success in obtaining better performance than human-designed strategies. However, these learnable evolutionary algorithms are only applicable to single-objective optimization and cannot be applied to multi-objective optimization problems. In this study, we parameterize the mutation and crossover operators using the multi-head self-attention and the selection operator using a lightweight multilayer perceptron. We utilize the evolution strategy to train their parameters across multiple multi-objective optimization problems, resulting in the development of the Meta-Learned Multi-Objective Genetic Algorithm (Meta-MOGA). We compare Meta-MOGA with other multi-objective evolutionary algorithms on various test problems and evaluate its performance on untrained MOPs. The results demonstrate that our Meta-MOGA exhibits potential and generalizability.
AbstractList In the field of single objective optimization algorithms, learned evolutionary algorithms have achieved success in obtaining better performance than human-designed strategies. However, these learnable evolutionary algorithms are only applicable to single-objective optimization and cannot be applied to multi-objective optimization problems. In this study, we parameterize the mutation and crossover operators using the multi-head self-attention and the selection operator using a lightweight multilayer perceptron. We utilize the evolution strategy to train their parameters across multiple multi-objective optimization problems, resulting in the development of the Meta-Learned Multi-Objective Genetic Algorithm (Meta-MOGA). We compare Meta-MOGA with other multi-objective evolutionary algorithms on various test problems and evaluate its performance on untrained MOPs. The results demonstrate that our Meta-MOGA exhibits potential and generalizability.
Author Wu, Kai
Teng, Xiangyi
Li, Tianyu
Liu, Jing
Li, Xiaobin
Author_xml – sequence: 1
  givenname: Tianyu
  surname: Li
  fullname: Li, Tianyu
  email: 22171214741@stu.xidian.edu.cn
  organization: Xidian University,Guangzhou Institute of Technology,Guangzhou,China
– sequence: 2
  givenname: Kai
  surname: Wu
  fullname: Wu, Kai
  email: kwu@xidian.edu.cn
  organization: Xidian University,School of Artificial Intelligence,Xi'an,China
– sequence: 3
  givenname: Xiaobin
  surname: Li
  fullname: Li, Xiaobin
  email: 22171214784@stu.xidian.edu.cn
  organization: Xidian University,Guangzhou Institute of Technology,Guangzhou,China
– sequence: 4
  givenname: Xiangyi
  surname: Teng
  fullname: Teng, Xiangyi
  email: tengxiangyi@xidian.edu.cn
  organization: Xidian University,Guangzhou Institute of Technology,Guangzhou,China
– sequence: 5
  givenname: Jing
  surname: Liu
  fullname: Liu, Jing
  email: neouma@mail.xidian.edu.cn
  organization: Xidian University,Guangzhou Institute of Technology,Guangzhou,China
BookMark eNo1j8tOwzAQRY1EF1D6BwjlB1IyduzY3UVRSZEaZUPX1cQeF6PURcEg8feU1-pcncWR7jW7jKdIjN1BsQQozH2zbpSEslrygstvVQoAfsEWpjJaCJDiLPQVW3WUMO_6tl5lP3MknGKIh6x7H1PI--GFbAoflLUUKQWb1ePhNIX0fLxhM4_jGy3-OGe7h_VTs8m3ffvY1Ns8QKVTboxAJ6mU3kmLqAZdedSKa2cHQdxh6TwYbmyh0GpwnixJdaZzVvpBijm7_e0GItq_TuGI0-f-_5L4AsNiRjk
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/CEC65147.2025.11043112
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331534318
EndPage 4
ExternalDocumentID 11043112
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  funderid: 10.13039/501100001809
– fundername: Research and Development
  funderid: 10.13039/100006190
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i178t-993ad5e45fd5caa6b87fa8628dcb3e2da4df1929c06ac81dfece561dfddc5fb53
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001539410900180&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Jul 02 05:55:41 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i178t-993ad5e45fd5caa6b87fa8628dcb3e2da4df1929c06ac81dfece561dfddc5fb53
PageCount 4
ParticipantIDs ieee_primary_11043112
PublicationCentury 2000
PublicationDate 2025-June-8
PublicationDateYYYYMMDD 2025-06-08
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-8
  day: 08
PublicationDecade 2020
PublicationTitle 2025 IEEE Congress on Evolutionary Computation (CEC)
PublicationTitleAbbrev CEC
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.9111328
Snippet In the field of single objective optimization algorithms, learned evolutionary algorithms have achieved success in obtaining better performance than...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Evolutionary computation
Evolutionary multi-objective optimization algorithms
Genetic algorithms
Meta-learning
Metalearning
Multi-objective optimization
Multilayer perceptrons
Optimization
Title Meta-MOGA: Meta-learning Multi-Objective Genetic Algorithm
URI https://ieeexplore.ieee.org/document/11043112
WOSCitedRecordID wos001539410900180&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LTgMhFCXauHClxhrfmYVb-pgOA3TXNK0u7GOhSXcNcC-1RtumTv1-L3SqceHCHSEkhEc45wLnHsbujHIKMKfYxOiUE78Frpy2HJpeC_TOtjCmzH-Uw6GaTPS4FKtHLQwixs9nWAvF-JYPS7cJV2V1girCu-ApvC9lvhVrlarfZkPXu71uTvgvKepLRW3X-JdtSkSN_tE_-ztm1R_9XTL-RpYTtoeLU9YeYGH4YHTfaSexWBo-zJIoouUj-7o9vJKQSpr2Q9J5my0p9n95r7Lnfu-p-8BL5wM-b0pVcCINBgRmwoNwxuRWSW8o9lAQJi8Fk4EnaqZdIzeOGKdHh0SEwAM44a1onbHKYrnAc5ZImwZvKqmEzTNpnIYMQ0r8FEF5D40LVg0Dn662yS2muzFf_lF_xQ7D9MbfUuqaVYr1Bm_Ygfss5h_r27gkX6Vgjxk
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwMhECammuhJjTW-3YNX-tguC_TWNK019nWoSW8NMEOt0a2pW3-_QLcaDx68EUJCZiDMN8A3HyF3ShgBmLrcRMmYOnwLVBipKdStZGiNbmAomd_nw6GYTuW4IKsHLgwihs9nWPHN8JYPS7P2V2VVF6pcvPOawrteOqugaxW833pNVtudduoQAHd5X8wq2-G_hFNC3Oge_nPGI1L-YeBF4-_Yckx2MDshzQHmig5G961mFJqF5MM8CjRaOtIvm-Mr8sWk3Y6IWq_zpcv-n9_K5KnbmbR7tNA-oIs6Fzl1sEEBw4RZYEapVAtulcs-BHj3xaASsA6cSVNLlXGY06JBB4XAAhhmNWucklK2zPCMRFzHXp2KC6bThCsjIUFfFD9GENZC7ZyUveGz9015i9nW5os_-m_Jfm8y6M_6D8PHS3LgXR3-TokrUspXa7wme-YzX3ysbsLyfAFL-JJi
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2025+IEEE+Congress+on+Evolutionary+Computation+%28CEC%29&rft.atitle=Meta-MOGA%3A+Meta-learning+Multi-Objective+Genetic+Algorithm&rft.au=Li%2C+Tianyu&rft.au=Wu%2C+Kai&rft.au=Li%2C+Xiaobin&rft.au=Teng%2C+Xiangyi&rft.date=2025-06-08&rft.pub=IEEE&rft.spage=1&rft.epage=4&rft_id=info:doi/10.1109%2FCEC65147.2025.11043112&rft.externalDocID=11043112