A hybrid neural combinatorial optimization framework assisted by automated algorithm design

In recent years, the application of Neural Combinatorial Optimization (NCO) techniques in Combinatorial Optimization (CO) has emerged as a popular and promising research direction. Currently, there are mainly two types of NCO, namely, the Constructive Neural Combinatorial Optimization (CNCO) and the...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Complex & intelligent systems Ročník 10; číslo 6; s. 8233 - 8247
Hlavní autori: Ma, Liang, Hao, Xingxing, Zhou, Wei, He, Qianbao, Zhang, Ruibang, Chen, Li
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Cham Springer International Publishing 01.12.2024
Springer Nature B.V
Springer
Predmet:
ISSN:2199-4536, 2198-6053
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract In recent years, the application of Neural Combinatorial Optimization (NCO) techniques in Combinatorial Optimization (CO) has emerged as a popular and promising research direction. Currently, there are mainly two types of NCO, namely, the Constructive Neural Combinatorial Optimization (CNCO) and the Perturbative Neural Combinatorial Optimization (PNCO). The CNCO generally trains an encoder-decoder model via supervised learning to construct solutions from scratch. It exhibits high speed in construction process, however, it lacks the ability for sustained optimization due to the one-shot mapping, which bounds its potential for application. Instead, the PNCO generally trains neural network models via deep reinforcement learning (DRL) to intelligently select appropriate human-designed heuristics to improve existing solutions. It can achieve high-quality solutions but at the cost of high computational demand. To leverage the strengths of both approaches, we propose to hybrid the CNCO and PNCO by designing a hybrid framework comprising two stages, in which the CNCO is the first stage and the PNCO is the second. Specifically, in the first stage, we utilize the attention model to generate preliminary solutions for given CO instances. In the second stage, we employ DRL to intelligently select and combine appropriate algorithmic components from improvement pool, perturbation pool, and prediction pool to continuously optimize the obtained solutions. Experimental results on synthetic and real Capacitated Vehicle Routing Problems (CVRPs) and Traveling Salesman Problems(TSPs) demonstrate the effectiveness of the proposed hybrid framework with the assistance of automated algorithm design.
AbstractList Abstract In recent years, the application of Neural Combinatorial Optimization (NCO) techniques in Combinatorial Optimization (CO) has emerged as a popular and promising research direction. Currently, there are mainly two types of NCO, namely, the Constructive Neural Combinatorial Optimization (CNCO) and the Perturbative Neural Combinatorial Optimization (PNCO). The CNCO generally trains an encoder-decoder model via supervised learning to construct solutions from scratch. It exhibits high speed in construction process, however, it lacks the ability for sustained optimization due to the one-shot mapping, which bounds its potential for application. Instead, the PNCO generally trains neural network models via deep reinforcement learning (DRL) to intelligently select appropriate human-designed heuristics to improve existing solutions. It can achieve high-quality solutions but at the cost of high computational demand. To leverage the strengths of both approaches, we propose to hybrid the CNCO and PNCO by designing a hybrid framework comprising two stages, in which the CNCO is the first stage and the PNCO is the second. Specifically, in the first stage, we utilize the attention model to generate preliminary solutions for given CO instances. In the second stage, we employ DRL to intelligently select and combine appropriate algorithmic components from improvement pool, perturbation pool, and prediction pool to continuously optimize the obtained solutions. Experimental results on synthetic and real Capacitated Vehicle Routing Problems (CVRPs) and Traveling Salesman Problems(TSPs) demonstrate the effectiveness of the proposed hybrid framework with the assistance of automated algorithm design.
In recent years, the application of Neural Combinatorial Optimization (NCO) techniques in Combinatorial Optimization (CO) has emerged as a popular and promising research direction. Currently, there are mainly two types of NCO, namely, the Constructive Neural Combinatorial Optimization (CNCO) and the Perturbative Neural Combinatorial Optimization (PNCO). The CNCO generally trains an encoder-decoder model via supervised learning to construct solutions from scratch. It exhibits high speed in construction process, however, it lacks the ability for sustained optimization due to the one-shot mapping, which bounds its potential for application. Instead, the PNCO generally trains neural network models via deep reinforcement learning (DRL) to intelligently select appropriate human-designed heuristics to improve existing solutions. It can achieve high-quality solutions but at the cost of high computational demand. To leverage the strengths of both approaches, we propose to hybrid the CNCO and PNCO by designing a hybrid framework comprising two stages, in which the CNCO is the first stage and the PNCO is the second. Specifically, in the first stage, we utilize the attention model to generate preliminary solutions for given CO instances. In the second stage, we employ DRL to intelligently select and combine appropriate algorithmic components from improvement pool, perturbation pool, and prediction pool to continuously optimize the obtained solutions. Experimental results on synthetic and real Capacitated Vehicle Routing Problems (CVRPs) and Traveling Salesman Problems(TSPs) demonstrate the effectiveness of the proposed hybrid framework with the assistance of automated algorithm design.
Author Hao, Xingxing
Ma, Liang
Zhou, Wei
Chen, Li
Zhang, Ruibang
He, Qianbao
Author_xml – sequence: 1
  givenname: Liang
  surname: Ma
  fullname: Ma, Liang
  organization: Northwest University
– sequence: 2
  givenname: Xingxing
  orcidid: 0000-0002-3590-2392
  surname: Hao
  fullname: Hao, Xingxing
  email: xingxing.hao@nwu.edu.cn
  organization: Northwest University
– sequence: 3
  givenname: Wei
  surname: Zhou
  fullname: Zhou, Wei
  organization: Northwest University
– sequence: 4
  givenname: Qianbao
  surname: He
  fullname: He, Qianbao
  organization: Northwest University
– sequence: 5
  givenname: Ruibang
  surname: Zhang
  fullname: Zhang, Ruibang
  organization: Northwest University
– sequence: 6
  givenname: Li
  surname: Chen
  fullname: Chen, Li
  organization: Northwest University
BookMark eNp9UbtOHDEUtSIiBQg_kGok6oHrB-NxiVACSEg0SZXCun4t3uyMF9uraPP18e5EoaO6D52XdM7IyZxmT8gXClcUQF4XAVLIHpjogQ4APftAThlVYz_ADT857qoXN3z4RC5KWQMAlXLkwE7Jz9vuZW9ydN3sdxk3nU2TiTPWlGO70rbGKf7BGtPchYyT_53yrw5LiaV615l9h7uaJjwcuFk1Vn2ZOudLXM2fyceAm-Iv_s1z8uPb1-93D_3T8_3j3e1Tb1um2g-jdYGZ4EQwynlpgqIGleA8cAhBMk7HgckWV0igbBDBKikZGGTomPX8nDwuui7hWm9znDDvdcKoj4-UVxpzjXbjtfF2DKOTbDBKCO_UoBRzVLpmba3BpnW5aG1zet35UvU67fLc4mtOaXNVLUtDsQVlcyol-_DflYI-dKKXTnTLrI-d6AOJL6TSwPPK5zfpd1h_AaIekis
Cites_doi 10.1007/BF00992696
10.1287/ijoc.3.4.376
10.1109/TII.2020.3031409
10.1007/s40747-022-00884-6
10.1016/j.eswa.2022.119461
10.1007/s40747-021-00635-z
10.1007/s40747-021-00507-6
10.1016/j.ins.2023.119639
10.1016/j.eswa.2021.115493
10.1109/TITS.2019.2929020
10.1007/978-3-319-93031-2_12
10.1109/TG.2019.2942773
10.1109/TEVC.2022.3197298
10.1145/3583133.3596303
10.1109/MCI.2020.2976182
10.1007/s40747-021-00288-y
10.1016/j.ejor.2016.08.012
ContentType Journal Article
Copyright The Author(s) 2024
The Author(s) 2024. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: The Author(s) 2024
– notice: The Author(s) 2024. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID C6C
AAYXX
CITATION
8FE
8FG
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
HCIFZ
P5Z
P62
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
DOA
DOI 10.1007/s40747-024-01600-2
DatabaseName Springer Nature OA Free Journals
CrossRef
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
ProQuest Central
ProQuest Technology Collection
ProQuest One Community College
ProQuest Central Korea
SciTech Premium Collection
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Publicly Available Content Database
Advanced Technologies & Aerospace Collection
Technology Collection
ProQuest One Academic Middle East (New)
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest One Academic Eastern Edition
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Technology Collection
ProQuest SciTech Collection
ProQuest Central China
ProQuest Central
Advanced Technologies & Aerospace Database
ProQuest One Applied & Life Sciences
ProQuest One Academic UKI Edition
ProQuest Central Korea
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
DatabaseTitleList
Publicly Available Content Database

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: PIMPY
  name: Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Mathematics
EISSN 2198-6053
EndPage 8247
ExternalDocumentID oai_doaj_org_article_bec8f8d726b944ed96992d17dfb9ccba
10_1007_s40747_024_01600_2
GrantInformation_xml – fundername: Key Research and Development Projects of Shaanxi Province
  grantid: 2020KW-068
  funderid: http://dx.doi.org/10.13039/501100015401
– fundername: National Natural Science Foundation of China
  grantid: 62106199
  funderid: http://dx.doi.org/10.13039/501100001809
– fundername: General Project of Education of Shannxi Provincial Government
  grantid: 22JK058
GroupedDBID 0R~
8FE
8FG
AAJSJ
AAKKN
ABEEZ
ABFTD
ACACY
ACGFS
ACULB
ADINQ
ADMLS
AFGXO
AFKRA
AHBYD
AHSBF
AHYZX
ALMA_UNASSIGNED_HOLDINGS
AMKLP
ARAPS
ASPBG
AVWKF
BAPOH
BENPR
BGLVJ
C24
C6C
CCPQU
EBLON
EBS
EJD
GROUPED_DOAJ
HCIFZ
IAO
ISR
ITC
M~E
OK1
P62
PIMPY
PROAC
RSV
SOJ
AASML
AAYXX
AFFHD
CITATION
PHGZM
PHGZT
PQGLB
ABUWG
AZQEC
DWQXO
PKEHL
PQEST
PQQKQ
PQUKI
PRINS
ID FETCH-LOGICAL-c453t-68cdf2bfd4fb9de7bf91ba9433f30ff723186273024701264fc97720ba2ad2ce3
IEDL.DBID P5Z
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001292349300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2199-4536
IngestDate Fri Oct 03 12:52:58 EDT 2025
Wed Oct 08 14:21:58 EDT 2025
Sat Nov 29 05:49:04 EST 2025
Fri Feb 21 02:37:08 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 6
Keywords Neural combinatorial optimization
Transformer
Automated algorithm design
Reinforcement learning
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c453t-68cdf2bfd4fb9de7bf91ba9433f30ff723186273024701264fc97720ba2ad2ce3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-3590-2392
OpenAccessLink https://www.proquest.com/docview/3117209862?pq-origsite=%requestingapplication%
PQID 3117209862
PQPubID 2044308
PageCount 15
ParticipantIDs doaj_primary_oai_doaj_org_article_bec8f8d726b944ed96992d17dfb9ccba
proquest_journals_3117209862
crossref_primary_10_1007_s40747_024_01600_2
springer_journals_10_1007_s40747_024_01600_2
PublicationCentury 2000
PublicationDate 20241200
PublicationDateYYYYMMDD 2024-12-01
PublicationDate_xml – month: 12
  year: 2024
  text: 20241200
PublicationDecade 2020
PublicationPlace Cham
PublicationPlace_xml – name: Cham
– name: Heidelberg
PublicationTitle Complex & intelligent systems
PublicationTitleAbbrev Complex Intell. Syst
PublicationYear 2024
Publisher Springer International Publishing
Springer Nature B.V
Springer
Publisher_xml – name: Springer International Publishing
– name: Springer Nature B.V
– name: Springer
References Chen X, Tian Y et al (2019) Learning to perform local rewriting for combinatorial optimization. In: 2019 Neural information processing systems (NIPS). arXiv preprint http://arxiv.org/abs/1810.00337
YiWQuRJiaoLAutomated design of metaheuristics using reinforcement learning within a novel general search frameworkIEEE Trans Evol Comput20232741072108410.1109/TEVC.2022.3197298
Gao L, Chen M, Chen Q et al (2020) Learn to design the heuristics for vehicle routing problem. arXiv preprint http://arxiv.org/abs/2002.08539
Du Y, Fu T, Sun J, et al (2022) Molgensurvey: a systematic survey in machine learning models for molecule design. arXiv preprint http://arxiv.org/abs/2203.14500
David A, Ribert B, Vasek C et al (2006) Concorde tsp solver. http://www.math.uwaterloo.ca/tsp/concorde
Meng W, Qu R (2023) Sequential Rule Mining for Automated Design of Meta-heuristics. In: Proceedings of the Companion Conference on Genetic and Evolutionary Computation (GECCO). arXiv preprint https://doi.org/10.1145/3583133.3596303
XinLSongWCaoZMulti-decoder attention model with embedding glimpse for solving vehicle routing problemsProc AAAI Conf Artificial Intell202135131204212049
Laurent Perron, Vincent Furnon (2023) Or-tools, URL https://developers.google.com/optimization
YiWQuRAutomated design of search algorithms based on reinforcement learningInform Sci202364910.1016/j.ins.2023.119639
Xin L, Song W, Cao Z et al (2020) Step-wise deep learning models for solving routing problems. IEEE Trans Ind Inform 17(7):4861–4871
Bello I, Pham H, Le QV, Norouzi M, Bengio S (2017) Neural combinatorial optimization with reinforcement learning. In: 2017 International conference on learning representations (ICLR). arXiv preprint http://arxiv.org/abs/1611.09940
YiWQuRJiaoLAutomated algorithm design using proximal policy optimisation with identified featuresExpert Syst Appl202321610.1016/j.eswa.2022.119461
LloydHAmosMSolving Sudoku with ant colony optimizationIEEE Trans Games201912330231110.1109/TG.2019.2942773
VeresMMoussaMDeep learning for intelligent transportation systems: A survey of emerging trendsIEEE Trans Intell Trans Syst20192183152316810.1109/TITS.2019.2929020
Chen X, Tian Y (2019) Learning to perform local rewriting for combinatorial optimization. 33rd Conference on Neural Information Processing Systems (NIPS). Vancouver, Canada, pp 6278–6289
Kool W, van Hoof H, Welling M (2019) Attention, learn to solve routing problems! In: 7th International conference on learning representations (ICLR). arXiv preprint http://arxiv.org/ abs/1803.08475
MengWQuRAutomated design of search algorithms: Learning on algorithmic componentsExpert Syst Appl202118510.1016/j.eswa.2021.115493
QuRKendallGPillayNThe General Combinatorial Optimization Problem: Towards Automated Algorithm DesignIEEE Comput Intell Mag2020152142310.1109/MCI.2020.2976182
UchoaEPecinDPessoaANew benchmark instances for the capacitated vehicle routing problemEuro J Oper Res20172573845858357112710.1016/j.ejor.2016.08.012
ZhengJWangLWangSSolving two-stage stochastic route-planning problem in milliseconds via end-to-end deep learningComplex Intell Syst2021731207122210.1007/s40747-021-00288-y
Liu F, Tong X, Yuan M, et al (2024) Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model. arXiv preprint arXiv:2401.02051V2
HelsgaunKeldAn extension of the lin-kernighan-helsgaun tsp solver for constrained traveling salesman and vehicle routing problems2017RoskildeRoskilde University
Gurobi Optimization, LLC (2023) Gurobi Optimizer Reference Manual. https://www.gurobi.com
Zhou C, Lin X, Wang Z, et al (2024) Instance-Conditioned Adaptation for Large-scale Generalization of Neural Combinatorial Optimization. arXiv preprint arXiv:2405.01906
ReineltGerhardTSPLIB-a traveling salesman problem libraryORSA J Comput19913437638410.1287/ijoc.3.4.376
Kingma D P, Ba J et al (2014) Adam: A method for stochastic optimization. In: 3rd International conference on learning representations (ICLR) arXiv preprint http://arxiv.org/abs/1412.6980
KwonYDChooJYoonIMatrix encoding networks for neural combinatorial optimizationAdv Neural Inform Process Syst20213451385149
Deudon M, Cournut P, Lacoste A et al (2018) Learning heuristics for the tsp by policy gradient. 15th International Conference on Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR). Springer, Netherlands, pp 170–181
HongLWoodwardJRÖzcanEHyper-heuristic approach: automatically designing adaptive mutation operators for evolutionary programmingComplex Intell Syst2021763135316310.1007/s40747-021-00507-6
Hottung A, Tierney K (2019) Neural large neighborhood search for the capacitated vehicle routing problem. In: 24th European Conference on Artificial Intelligence (ECAI).arXiv preprint http://arxiv.org/abs/1911.09539
Luo F, Lin X, Liu F et al (2023) Neural combinatorial optimization with heavy decoder: Toward large scale generalization. arXiv preprint http://arxiv.org/abs/2310.07985
WilliamsRJSimple statistical gradient-following algorithms for connectionist reinforcement learningMach Learn1992822925610.1007/BF00992696
KimMParkJLearning collaborative policies to solve NP-hard routing problemsAdv Neural Inform Process Syst2021341041810430
Cheng H, Zheng H, Cong Y et al (2023) Select and Optimize: Learning to aolve large-scale TSP instances. In: 26th International Conference on Artificial Intelligence and Statistics 206:1219-1231
KwonYDChooJKimBPomo: Policy optimization with multiple optima for reinforcement learningAdv Neural Inform Process Syst2020332118821198
Schulman J, Wolski F, Dhariwal P et al (2017). Proximal policy optimization algorithms. arXiv preprint http://arxiv.org/abs/1707.06347
LiSLuoTWangLTourism route optimization based on improved knowledge ant colony algorithmComplex Intell Syst2022853973398810.1007/s40747-021-00635-z
ZhongJFengYTangSA collaborative neurodynamic optimization algorithm to traveling salesman problemComplex Intell Syst2023921809182110.1007/s40747-022-00884-6
Lu H, Zhang X, Yang S (2019) A learning-based iterative method for solving vehicle routing problems. In: 8th International conference on learning representations (ICLR)
Vinyals O, Fortunato M, Jaitly N (2015) Pointer networks. In: 2015 Neural information processing systems (NIPS), pp 2692-2700
1600_CR20
YD Kwon (1600_CR22) 2021; 34
1600_CR40
J Zheng (1600_CR12) 2021; 7
L Hong (1600_CR32) 2021; 7
1600_CR27
1600_CR28
1600_CR25
1600_CR26
1600_CR23
Gerhard Reinelt (1600_CR41) 1991; 3
W Yi (1600_CR9) 2023; 649
W Meng (1600_CR37) 2021; 185
J Zhong (1600_CR10) 2023; 9
S Li (1600_CR5) 2022; 8
W Yi (1600_CR8) 2023; 27
W Yi (1600_CR31) 2023; 216
Keld Helsgaun (1600_CR6) 2017
L Xin (1600_CR24) 2021; 35
1600_CR16
1600_CR3
1600_CR17
1600_CR39
1600_CR36
1600_CR1
1600_CR15
1600_CR34
1600_CR7
1600_CR13
1600_CR35
1600_CR11
1600_CR33
H Lloyd (1600_CR4) 2019; 12
YD Kwon (1600_CR18) 2020; 33
RJ Williams (1600_CR14) 1992; 8
1600_CR19
M Veres (1600_CR2) 2019; 21
M Kim (1600_CR21) 2021; 34
W Meng (1600_CR29) 2021; 185
R Qu (1600_CR30) 2020; 15
E Uchoa (1600_CR38) 2017; 257
References_xml – reference: Vinyals O, Fortunato M, Jaitly N (2015) Pointer networks. In: 2015 Neural information processing systems (NIPS), pp 2692-2700
– reference: Kingma D P, Ba J et al (2014) Adam: A method for stochastic optimization. In: 3rd International conference on learning representations (ICLR) arXiv preprint http://arxiv.org/abs/1412.6980
– reference: Hottung A, Tierney K (2019) Neural large neighborhood search for the capacitated vehicle routing problem. In: 24th European Conference on Artificial Intelligence (ECAI).arXiv preprint http://arxiv.org/abs/1911.09539
– reference: HelsgaunKeldAn extension of the lin-kernighan-helsgaun tsp solver for constrained traveling salesman and vehicle routing problems2017RoskildeRoskilde University
– reference: Gurobi Optimization, LLC (2023) Gurobi Optimizer Reference Manual. https://www.gurobi.com
– reference: David A, Ribert B, Vasek C et al (2006) Concorde tsp solver. http://www.math.uwaterloo.ca/tsp/concorde/
– reference: Chen X, Tian Y (2019) Learning to perform local rewriting for combinatorial optimization. 33rd Conference on Neural Information Processing Systems (NIPS). Vancouver, Canada, pp 6278–6289
– reference: VeresMMoussaMDeep learning for intelligent transportation systems: A survey of emerging trendsIEEE Trans Intell Trans Syst20192183152316810.1109/TITS.2019.2929020
– reference: LloydHAmosMSolving Sudoku with ant colony optimizationIEEE Trans Games201912330231110.1109/TG.2019.2942773
– reference: Xin L, Song W, Cao Z et al (2020) Step-wise deep learning models for solving routing problems. IEEE Trans Ind Inform 17(7):4861–4871
– reference: Schulman J, Wolski F, Dhariwal P et al (2017). Proximal policy optimization algorithms. arXiv preprint http://arxiv.org/abs/1707.06347
– reference: Liu F, Tong X, Yuan M, et al (2024) Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model. arXiv preprint arXiv:2401.02051V2
– reference: Luo F, Lin X, Liu F et al (2023) Neural combinatorial optimization with heavy decoder: Toward large scale generalization. arXiv preprint http://arxiv.org/abs/2310.07985
– reference: KimMParkJLearning collaborative policies to solve NP-hard routing problemsAdv Neural Inform Process Syst2021341041810430
– reference: Zhou C, Lin X, Wang Z, et al (2024) Instance-Conditioned Adaptation for Large-scale Generalization of Neural Combinatorial Optimization. arXiv preprint arXiv:2405.01906
– reference: ReineltGerhardTSPLIB-a traveling salesman problem libraryORSA J Comput19913437638410.1287/ijoc.3.4.376
– reference: HongLWoodwardJRÖzcanEHyper-heuristic approach: automatically designing adaptive mutation operators for evolutionary programmingComplex Intell Syst2021763135316310.1007/s40747-021-00507-6
– reference: LiSLuoTWangLTourism route optimization based on improved knowledge ant colony algorithmComplex Intell Syst2022853973398810.1007/s40747-021-00635-z
– reference: Du Y, Fu T, Sun J, et al (2022) Molgensurvey: a systematic survey in machine learning models for molecule design. arXiv preprint http://arxiv.org/abs/2203.14500
– reference: Lu H, Zhang X, Yang S (2019) A learning-based iterative method for solving vehicle routing problems. In: 8th International conference on learning representations (ICLR)
– reference: KwonYDChooJYoonIMatrix encoding networks for neural combinatorial optimizationAdv Neural Inform Process Syst20213451385149
– reference: Cheng H, Zheng H, Cong Y et al (2023) Select and Optimize: Learning to aolve large-scale TSP instances. In: 26th International Conference on Artificial Intelligence and Statistics 206:1219-1231
– reference: QuRKendallGPillayNThe General Combinatorial Optimization Problem: Towards Automated Algorithm DesignIEEE Comput Intell Mag2020152142310.1109/MCI.2020.2976182
– reference: WilliamsRJSimple statistical gradient-following algorithms for connectionist reinforcement learningMach Learn1992822925610.1007/BF00992696
– reference: Meng W, Qu R (2023) Sequential Rule Mining for Automated Design of Meta-heuristics. In: Proceedings of the Companion Conference on Genetic and Evolutionary Computation (GECCO). arXiv preprint https://doi.org/10.1145/3583133.3596303
– reference: XinLSongWCaoZMulti-decoder attention model with embedding glimpse for solving vehicle routing problemsProc AAAI Conf Artificial Intell202135131204212049
– reference: UchoaEPecinDPessoaANew benchmark instances for the capacitated vehicle routing problemEuro J Oper Res20172573845858357112710.1016/j.ejor.2016.08.012
– reference: YiWQuRAutomated design of search algorithms based on reinforcement learningInform Sci202364910.1016/j.ins.2023.119639
– reference: KwonYDChooJKimBPomo: Policy optimization with multiple optima for reinforcement learningAdv Neural Inform Process Syst2020332118821198
– reference: YiWQuRJiaoLAutomated design of metaheuristics using reinforcement learning within a novel general search frameworkIEEE Trans Evol Comput20232741072108410.1109/TEVC.2022.3197298
– reference: ZhongJFengYTangSA collaborative neurodynamic optimization algorithm to traveling salesman problemComplex Intell Syst2023921809182110.1007/s40747-022-00884-6
– reference: YiWQuRJiaoLAutomated algorithm design using proximal policy optimisation with identified featuresExpert Syst Appl202321610.1016/j.eswa.2022.119461
– reference: Chen X, Tian Y et al (2019) Learning to perform local rewriting for combinatorial optimization. In: 2019 Neural information processing systems (NIPS). arXiv preprint http://arxiv.org/abs/1810.00337
– reference: ZhengJWangLWangSSolving two-stage stochastic route-planning problem in milliseconds via end-to-end deep learningComplex Intell Syst2021731207122210.1007/s40747-021-00288-y
– reference: Bello I, Pham H, Le QV, Norouzi M, Bengio S (2017) Neural combinatorial optimization with reinforcement learning. In: 2017 International conference on learning representations (ICLR). arXiv preprint http://arxiv.org/abs/1611.09940
– reference: Gao L, Chen M, Chen Q et al (2020) Learn to design the heuristics for vehicle routing problem. arXiv preprint http://arxiv.org/abs/2002.08539
– reference: MengWQuRAutomated design of search algorithms: Learning on algorithmic componentsExpert Syst Appl202118510.1016/j.eswa.2021.115493
– reference: Laurent Perron, Vincent Furnon (2023) Or-tools, URL https://developers.google.com/optimization/
– reference: Kool W, van Hoof H, Welling M (2019) Attention, learn to solve routing problems! In: 7th International conference on learning representations (ICLR). arXiv preprint http://arxiv.org/ abs/1803.08475
– reference: Deudon M, Cournut P, Lacoste A et al (2018) Learning heuristics for the tsp by policy gradient. 15th International Conference on Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR). Springer, Netherlands, pp 170–181
– volume-title: An extension of the lin-kernighan-helsgaun tsp solver for constrained traveling salesman and vehicle routing problems
  year: 2017
  ident: 1600_CR6
– volume: 8
  start-page: 229
  year: 1992
  ident: 1600_CR14
  publication-title: Mach Learn
  doi: 10.1007/BF00992696
– volume: 3
  start-page: 376
  issue: 4
  year: 1991
  ident: 1600_CR41
  publication-title: ORSA J Comput
  doi: 10.1287/ijoc.3.4.376
– ident: 1600_CR23
  doi: 10.1109/TII.2020.3031409
– volume: 9
  start-page: 1809
  issue: 2
  year: 2023
  ident: 1600_CR10
  publication-title: Complex Intell Syst
  doi: 10.1007/s40747-022-00884-6
– ident: 1600_CR11
– volume: 216
  year: 2023
  ident: 1600_CR31
  publication-title: Expert Syst Appl
  doi: 10.1016/j.eswa.2022.119461
– ident: 1600_CR34
– volume: 8
  start-page: 3973
  issue: 5
  year: 2022
  ident: 1600_CR5
  publication-title: Complex Intell Syst
  doi: 10.1007/s40747-021-00635-z
– ident: 1600_CR36
– ident: 1600_CR13
– ident: 1600_CR19
– ident: 1600_CR15
– ident: 1600_CR27
– volume: 35
  start-page: 12042
  issue: 13
  year: 2021
  ident: 1600_CR24
  publication-title: Proc AAAI Conf Artificial Intell
– volume: 7
  start-page: 3135
  issue: 6
  year: 2021
  ident: 1600_CR32
  publication-title: Complex Intell Syst
  doi: 10.1007/s40747-021-00507-6
– ident: 1600_CR3
– volume: 649
  year: 2023
  ident: 1600_CR9
  publication-title: Inform Sci
  doi: 10.1016/j.ins.2023.119639
– volume: 33
  start-page: 21188
  year: 2020
  ident: 1600_CR18
  publication-title: Adv Neural Inform Process Syst
– ident: 1600_CR25
– ident: 1600_CR1
– volume: 185
  year: 2021
  ident: 1600_CR29
  publication-title: Expert Syst Appl
  doi: 10.1016/j.eswa.2021.115493
– ident: 1600_CR40
– volume: 21
  start-page: 3152
  issue: 8
  year: 2019
  ident: 1600_CR2
  publication-title: IEEE Trans Intell Trans Syst
  doi: 10.1109/TITS.2019.2929020
– ident: 1600_CR16
– volume: 185
  year: 2021
  ident: 1600_CR37
  publication-title: Expert Syst Appl
  doi: 10.1016/j.eswa.2021.115493
– ident: 1600_CR7
– ident: 1600_CR17
  doi: 10.1007/978-3-319-93031-2_12
– ident: 1600_CR39
– volume: 34
  start-page: 10418
  year: 2021
  ident: 1600_CR21
  publication-title: Adv Neural Inform Process Syst
– ident: 1600_CR35
– volume: 12
  start-page: 302
  issue: 3
  year: 2019
  ident: 1600_CR4
  publication-title: IEEE Trans Games
  doi: 10.1109/TG.2019.2942773
– volume: 27
  start-page: 1072
  issue: 4
  year: 2023
  ident: 1600_CR8
  publication-title: IEEE Trans Evol Comput
  doi: 10.1109/TEVC.2022.3197298
– volume: 34
  start-page: 5138
  year: 2021
  ident: 1600_CR22
  publication-title: Adv Neural Inform Process Syst
– ident: 1600_CR33
– ident: 1600_CR28
  doi: 10.1145/3583133.3596303
– volume: 15
  start-page: 14
  issue: 2
  year: 2020
  ident: 1600_CR30
  publication-title: IEEE Comput Intell Mag
  doi: 10.1109/MCI.2020.2976182
– volume: 7
  start-page: 1207
  issue: 3
  year: 2021
  ident: 1600_CR12
  publication-title: Complex Intell Syst
  doi: 10.1007/s40747-021-00288-y
– ident: 1600_CR20
– ident: 1600_CR26
– volume: 257
  start-page: 845
  issue: 3
  year: 2017
  ident: 1600_CR38
  publication-title: Euro J Oper Res
  doi: 10.1016/j.ejor.2016.08.012
SSID ssj0001778302
ssib044733412
ssib045327741
Score 2.2753367
Snippet In recent years, the application of Neural Combinatorial Optimization (NCO) techniques in Combinatorial Optimization (CO) has emerged as a popular and...
Abstract In recent years, the application of Neural Combinatorial Optimization (NCO) techniques in Combinatorial Optimization (CO) has emerged as a popular and...
SourceID doaj
proquest
crossref
springer
SourceType Open Website
Aggregation Database
Index Database
Publisher
StartPage 8233
SubjectTerms Algorithms
Automated algorithm design
Automation
Combinatorial analysis
Complexity
Computational Intelligence
Data Structures and Information Theory
Deep learning
Design optimization
Encoders-Decoders
Engineering
Machine learning
Neural combinatorial optimization
Neural networks
Optimization
Original Article
Reinforcement learning
Supervised learning
Transformer
Traveling salesman problem
Vehicle routing
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA4iHvQgPrG6Sg7eNNhN0qY5qrh4cfGgIHgIzcsVdFd2q-C_d5I-dhXEi8e2adNMvna-aSffIHQMEYLVonAkMzYj3NKMyCLThHlHqfQhD6MuNiGGw-LhQd4ulPoKOWG1PHBtuDPoo_CFFTTXknNnZS4ltdCD19IYHakRsJ6FYAqQxLlgjM8dN88YFW2Nmfj1RYggfBUqz_WlJDz-w9zv1tXxICtPwH2RIMCWEvrNa0Vx_2-M9MdP1OibBhtovSGV-LwezCZacuMttHbTKbLOttHjOR59htVZOChYQmNAGgTFIeQGBOIJvDlemyWZ2LcJWxiYdYCBxfoTl-_VBK4GG-XLE5xVjV6xjfkfO-h-cHV3eU2awgrEwEgrkhfGeqq95WBE64T2sq9LyRnzLPVeAOeDQAeefcoFOLCcewM0kaa6pKWlxrFdtDyejN0ewr4MJDJzxkkIFR0vbMrL3DNrfOpLnSXopDWceqv1M1SnlBzNrKAXFc2saIIugm27lkH7Ou4ARKgGEeovRCSo186Mah7ImWJ9YGqphGEl6LSdrfnh329p_z9u6QCt0oCmmAbTQ8vV9N0dohXzUT3PpkcRul9XAu6N
  priority: 102
  providerName: Directory of Open Access Journals
– databaseName: SpringerOpen
  dbid: C24
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV05T8MwFLZQYYCBG1EueWADS6ntxPFYEBULFQNISAyWT4pEW9SmSPx7nt2kHBIDjE58xM_P74jf-4zQKXgIzojSk9y6nHBHcyLL3BAWPKUyxDiM-WUTot8vHx7kbZ0UNm2i3ZsjySSpF8luPGK9E9ApJKKiZQQE73LeKWXk68tPzHHOBWO8VtrpT4sQEeQq3jLXkZLwdF558Hu33zRUAvL_Zn3-ODBNeqi38b8ZbKL12u7E3TmjbKElP9pGa1_QCKF0s4Bwne6gxy4evMd0LhwhL6EpjAFedPTRgWXxGETNsM7hxKGJ8MJgike-cdi8Yz2rxtAbFPTLE7SqBkPsUsDILrrvXd1dXpP6JgZigVwVKUrrAjXB8WCk88IE2TFacsYCy0IQYCSCZwTCgnIBGq_gwYJdSTOjqXbUeraHWqPxyO8jHHS0OnNvvQTf0vPSZVwXgTkbsqBN3kZnDfXV6xxwQy2glRMBFYyiEgEVbaOLuECLmhEsOz0YT55UvfcUsGkZSidoYSTn3slCSuqASWEy1hrdRkfN8qp6B08V64Bpl0mYVhudN8v5-fr3Tzr4W_VDtEojR6QImSPUqiYzf4xW7Fv1PJ2cJM7-AMrq8Rc
  priority: 102
  providerName: Springer Nature
Title A hybrid neural combinatorial optimization framework assisted by automated algorithm design
URI https://link.springer.com/article/10.1007/s40747-024-01600-2
https://www.proquest.com/docview/3117209862
https://doaj.org/article/bec8f8d726b944ed96992d17dfb9ccba
Volume 10
WOSCitedRecordID wos001292349300001&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
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2198-6053
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001778302
  issn: 2199-4536
  databaseCode: DOA
  dateStart: 20150101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2198-6053
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssib044733412
  issn: 2199-4536
  databaseCode: M~E
  dateStart: 20150101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 2198-6053
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001778302
  issn: 2199-4536
  databaseCode: P5Z
  dateStart: 20151201
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 2198-6053
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001778302
  issn: 2199-4536
  databaseCode: BENPR
  dateStart: 20151201
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 2198-6053
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001778302
  issn: 2199-4536
  databaseCode: PIMPY
  dateStart: 20151201
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVAVX
  databaseName: SpringerOpen
  customDbUrl:
  eissn: 2198-6053
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001778302
  issn: 2199-4536
  databaseCode: C24
  dateStart: 20151201
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB7RlgMceFdsaVc-cAOLrO3E8Qm1VSs4dBUhkAocLD_bSu2m7KZI_feMvcmuigSXHhM7duwZz8MefwPwFj0Eb2UdaOl8SYVnJVV1aSmPgTEVUxzGMtmEnE7r01PV9Btuiz6scpCJWVD71qU98g98gqq2UGiAf7z-RVPWqHS62qfQ2ICthJKQFmZT_hj4SQjJuVirb1FyJodMM3kPRsoEf5Xyz02UoiKfZO6sbteJBC5PUYnRBMNWUHZHd2WI_zt26V9HqVlDHT-979iewZPeNiX7S2Z6Dg_C7AU8PlkBuy5ews99cn6bLnmRBISJlbED9K2T546MTFoUQFf9zU4Sh7gvggZ64iZP7C0xN12LreGDuTzDr7rzK-JzGMkr-HZ89PXwE-3zM1CHU9XRqnY-Mhu9iFb5IG1UE2uU4DzyIkaJpiMOCUUIExL1YCWiQ2uTFdYw45kLfBs2Z-0svAYSTbJFy-CCQo8ziNoXwlSRexeLaGw5gnfDzOvrJQyHXgEuZzpp7EVnOmk2goNEnFXNBKGdX7TzM92vSI3MW8faS1ZZJUTwqlKKeWRdHIxz1oxgdyCW7tf1Qq8pNYL3A7nXxf_-pZ3_t_YGHrHEaDlOZhc2u_lN2IOH7nd3sZiPYevgaNp8GcPGIRPjvG0wzpyOJc3nk-b7HwjE__A
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VggQceCO2FPABTmCRtZ04PiBUHlWrtqseilTBwfjZVqKbspuC9k_xGxl7k10VCW49cEzieOL4m_GMPQ-A52gheCvrQEvnSyo8K6mqS0t5DIypmPww5sUm5GhUHx6q_RX41cfCJLfKXiZmQe0bl_bIX_MhLrWFQgX87dl3mqpGpdPVvoTGHBY7YfYTTbbpm-0POL8vGNv8ePB-i3ZVBagTJW9pVTsfmY1eRKt8kDaqoTVKcB55EaNEhQeJIPCZkCi9KxEd6kissIYZz1zg2O8VuCoEGkvIP_vl5x6_QkjOxVJdQHJM9pVt8p6PlCndVqp3N1SKinxyuraI5hMpmT1FujSlfSsou7BW5pICF_TgP45u84q4eft_-5d34Fane5ONObPchZUwvgc39xaJa6f34csGOZ6lIDaSEn1iYxyQPRmnnQlkVNKggD3tIldJ7P3aCBogiVs8sTNiztsGe8ML8-0I32qPT4nPbjIP4NOljO4hrI6bcXgEJJqka5fBBYUWdRC1L4SpIvcuFtHYcgAv-5nWZ_M0I3qRUDrjQiMVnXGh2QDeJTAsWqYU4flGMznSncTRyJx1rL1klVVCBK8qpZhH1sTBOGfNANZ7cOhObk31EhkDeNXDa_n475-09u_ensH1rYO9Xb27Pdp5DDdYAnn2CVqH1XZyHp7ANfejPZlOnmaOIvD1smH3G18JWBU
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB6hFiE48EZsW8AHbmA1aztxfCxtVyBg1QNIlThYfk2LRHer3RSp_56xN9m2SD0gjk78iD1jz0xm5jPAW7IQotdt4nWINVdR1Ny0tecSkxAGcxzG6rIJPZ22x8fm6FoWf4l2H1ySq5yGjNI063bPI-6uE99Uxn3nJF94RkirOB3Cm9kjlc2v_Sv8caW0lKoX4OWvi9YZ8CrfODc2hqviu9y6vdsb0qqA-t_QRP9ynhaZNHn0_7N5DA97fZTtrRjoCdxJs6fw4BpKIZW-rqFdl8_gxx47vcxpXixDYVJTGo-s62y7EyuzOR1BZ31uJ8Mh8ouRip75KTJ_ydxFN6feqOB-nVCr7vSMxRJI8hy-Tw6_7X_k_Q0NPNDSdbxpQ0ThMSr0Jibt0Yy9M0pKlBWiJuWRLCY6RITSJAkbhYH0TVF5J1wUIckXsDGbz9JLYOiyNlqnkAzZnEm1sVKuQRkDVuh8PYJ3AyXs-QqIw64hl8sCWhrFlgW0YgQfMrHWNTOIdnkwX5zYfk9aYt8W26hF441SKZrGGBGJeWkyIXg3gp2B1Lbf2Usrx6TyVYamNYL3A2mvXt_-SVv_Vv0N3Ds6mNgvn6aft-G-yMxRgmh2YKNbXKRXcDf87n4uF68Lw_8BhhL84A
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%3Ajournal&rft.genre=article&rft.atitle=A+hybrid+neural+combinatorial+optimization+framework+assisted+by+automated+algorithm+design&rft.jtitle=Complex+%26+intelligent+systems&rft.au=Ma%2C+Liang&rft.au=Hao%2C+Xingxing&rft.au=Zhou%2C+Wei&rft.au=He%2C+Qianbao&rft.date=2024-12-01&rft.pub=Springer+Nature+B.V&rft.issn=2199-4536&rft.eissn=2198-6053&rft.volume=10&rft.issue=6&rft.spage=8233&rft.epage=8247&rft_id=info:doi/10.1007%2Fs40747-024-01600-2
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2199-4536&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2199-4536&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2199-4536&client=summon