计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (9): 309-323.doi: 10.11896/jsjkx.250600182

• 人工智能 • 上一篇    下一篇

基于梯度约束WGAN的平行权重关联与方向引导的大规模多目标优化算法

邓汉卿, 武向娟   

  1. 宁夏大学信息工程学院 银川 750021
    宁夏“东数西算”人工智能与信息安全重点实验室 银川 750021
  • 收稿日期:2025-06-24 修回日期:2025-10-11 出版日期:2026-09-15 发布日期:2026-09-10
  • 通讯作者: 武向娟(xjwu@nxu.edu.cn)
  • 作者简介:(dhq123@stu.nxu.edu.cn)
  • 基金资助:
    国家自然科学基金(62362056);宁夏回族自治区重点研发计划(2023BSB03016);宁夏自然科学基金(2023AAC05010)

Parallel Weight Association and Guided Direction Based WGAN with Gradient Penalty forLarge-scale Multi-objective Optimization

DENG Hanqing, WU Xiangjuan   

  1. School of Information Engineering,Ningxia University,Yinchuan 750021,China
    Ningxia Key Laboratory of Artificial Intelligence and Information Security for Channeling Computing Resources from the East to the West, Yinchuan 750021,China
  • Received:2025-06-24 Revised:2025-10-11 Published:2026-09-15 Online:2026-09-10
  • About author:DENG Hanqing,born in 1998,postgra-duate,is a member of CCF(No.Z9536G).His main research interest is large-scale multi-objective optimization.
    WU Xiangjuan,born in 1985,Ph.D,associate professor,is a member of CCF(No.R6177M).Her main research interests include evolutionary computation and multi-objective optimization.
  • Supported by:
    National Natural Science Foundation of China(62362056),Key R & D Program of Ningxia(2023BSB03016) and Natural Science Foundation of Ningxia(2023AAC05010).

PDF (PC)

298

摘要： 大规模多目标优化问题在工程领域广泛存在,随着决策变量增加,在有限资源内获取高质量后代极具挑战。生成对抗网络应用于大规模问题求解时存在模型坍塌、种群多样性不足等缺陷,导致优化性能下降。针对上述问题,提出一种基于梯度约束 Wasserstein 生成对抗网络的平行权重关联与方向引导的大规模多目标优化算法。该算法采用具有梯度约束的 Wasserstein 生成对抗网络来学习种群分布,快速生成优质后代。同时,为确保模型学习到更优的种群分布,设计了两个有效策略,生成兼具收敛性与多样性的训练样本集:一是平行权重关联策略,通过在高维决策空间构造平行权重关联方向,聚焦收敛潜力大的区域搜索,增强种群收敛性;二是方向引导策略,构建兼具多样性与收敛潜力的搜索方向,引导种群进化,保持种群多样性,从而避免陷入局部最优。在标准测试集和一个实际应用问题中进行了算法有效性验证,结果表明,所提算法在解集质量上显著优于当前多个先进大规模多目标进化算法,为该类问题提供了高效解决方案。

关键词: 大规模多目标优化, 进化算法, 对抗生成网络, 平行权重关联, 方向引导

Abstract: Large-scale multi-objective optimization problems are widely present in engineering fields.As the number of decision variables increases,obtaining high-quality offspring within limited resources becomes extremely challenging.When applied to solving large-scale problems,generative adversarial networks suffer from issues such as model collapse and insufficient population diversity,which lead to a decline in optimization performance.To address the above issue,this paper proposes a large-scale multi-objective optimization algorithm based on parallel weight association and guided direction-based Wasserstein generative adversarial networks with gradient penalty.The proposed algorithm employs a Wasserstein generative adversarial network with gradient penalty to learn the population distribution and rapidly generate high-quality offspring.To ensure that the model learns a more optimal population distribution,two effective strategies are designed to generate training sets that possess both convergence and diversity.Firstly,the parallel weight association strategy constructs parallel weight-associated directions in the high-dimensional decision space,focusing the search on areas with greater convergence potential,thereby enhancing population convergence.Secondly,the directional guidance strategy builds search directions that combine diversity and convergence potential to guide the population evolution,maintaining population diversity and avoiding local optima.The effectiveness of the algorithm has been verified on standard test sets and a real-world application problem.Experimental results show that the proposed algorithm signi-ficantly outperforms several current state-of-the-art large-scale multi-objective evolutionary algorithms in terms of solution set quality,providing an efficient solution for this type of problem.

Key words: Large-scale multi-objective optimization, Evolutionary algorithm, Generative adversarial network, Parallel weight association, Direction guidance

中图分类号: 

  • TP18
[1] SOFRONOVA E.Multi-Objective Optimization in Traffic Flow Control[C] //2023 9th International Conference on Control,Decision and Information Technologies(CoDIT).IEEE,2023:549-554.
[2] CHERIF H,BELHADJ J.Dynamics of Multi-Objective Energy Optimization in Multi-Energy Micro-Grids Based on Renewable Energy[C] //2023 9th International Conference on Control,Decision and Information Technologies(CoDIT).IEEE,2023:2199-2204.
[3] WANG F,ZHANG H,HAN M C,et al.Co-evolution Based Mixed-variable Multi-objective Particle SwarmOptimization for UAV Cooperative Multi-task Allocation Problem[J].Chinese Journal of Computers,2021,44(10):1967-1983.
[4] MA X,LIU F,QI Y,et al.A Multiobjective Evolutionary Algorithm Based on Decision Variable Analyses for Multiobjective Optimization Problems with Large-scale Variables[J].IEEE Transactions on Evolutionary Computation,2015,20(2):275-298.
[5] ZHANG X,TIAN Y,CHENG R,et al.A Decision VariableClustering-based Evolutionary Algorithm for Large-scale Many-objective Optimization[J].IEEE Transactions on Evolutionary Computation,2016,22(1):97-112.
[6] ZILLE H,ISHIBUCHI H,MOSTAGHIM S,et al.A Framework for Large-Scale Multiobjective Optimization Based on Problem Transformation[J].IEEE Transactions on Evolutionary Computation,2017,22(2):260-275.
[7] HE C,LI L,TIAN Y,et al.Accelerating Large-Scale Multiobjective Optimization via Problem Reformulation[J].IEEE Transactions on Evolutionary Computation,2019,23(6):949-961.
[8] QIN S,SUN C,JIN Y,et al.Large-Scale Evolutionary Multiobjective Optimization Assisted by Directed Sampling[J].IEEE Transactions on Evolutionary Computation,2021,25(4):724-738.
[9] HE C,CHENG R,TIAN Y,et al.Iterated Problem Reformulation for Evolutionary Large-Scale Multiobjective Optimization[C] //2020 IEEE Congress on Evolutionary Computation(CEC).IEEE,2020:1-8.
[10] LIU R,REN R,LIU J,et al.A Clustering and Dimensionality Reduction Based Evolutionary Algorithm for Large-Scale Multi-Objective Problems[J].Applied Soft Computing,2020,89:106120.
[11] TIAN Y,ZHENG X,ZHANG X,et al.Efficient Large-ScaleMultiobjective Optimization Based on A Competitive Swarm Optimizer[J].IEEE Transactions on Cybernetics,2019,50(8):3696-3708.
[12] HE C,CHENG R,YAZDANI D.Adaptive Offspring Generation for Evolutionary Large-Scale Multiobjective Optimization[J].IEEE Transactions on Systems,Man,and Cybernetics:Systems,2020,52(2):786-798.
[13] WU X,WANG Y,WANG Z.A Learning and Potential Area-Mining Evolutionary Algorithm for Large-Scale Multi-Objective Optimization[J].Expert Systems with Applications,2024,237:121563.
[14] ZHANG Y,WANG G G,LI K,et al.Enhancing MOEA/D with Information Feedback Models for Large-Scale Many-Objective Optimization[J].Information Sciences,2020,522:1-16.
[15] GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative Adversarial Nets[C] //Proceedings of the 28st International Conference on Neural Information Processing Systems.2014:2672-2680.
[16] HE C,HUANG S,CHENG R,et al.Evolutionary Multiobjec-tive Optimization Driven by Generative Adversarial Networks(GANs)[J].IEEE Transactions on Cybernetics,2020,51(6):3129-3142.
[17] GE H,ZHENG Z,HOU Y,et al.Learning to Evolve with Guiding Solutions Generated by Generative Adversarial Network[J].IEEE Transactions on Evolutionary Computation,2024,29(5):1834-1848.
[18] GULRAJANI I,AHMED F,ARJOVSKY M,et al.ImprovedTraining of Wasserstein Gans[C] //Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:5769-5779.
[19] KINGMA D P,WELLING M.Auto-Encoding Variational Bayes[J].arXiv:1312.6114,2013.
[20] HO J,JAIN A,ABBEEL P.Denoising Diffusion ProbabilisticModels[J].Advances in Neural Information Processing Systems,2020,33:6840-6851.
[21] YU N,LIU G,DUNDAR A,et al.Dual contrastive loss and attention for gans[C] //Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:6731-6742.
[22] LU Y X,LIU Z Y,LUO Y G,et al.Black-box Transferable Attack Method for Object Detection Based on GAN[J].Journal of Software,2024,35(7):3531-3550.
[23] YANG Z,CHAI Y,ANGUELOV D,et al.Surfelgan:Synthesizing realistic sensor data for autonomous driving[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:11118-11127.
[24] CHENG R,JIN Y,NARUKAWA K,et al.A Multiobjective Evolutionary Algorithm Using Gaussian Process-Based Inverse Modeling[J].IEEE Transactions on Evolutionary Computation,2015,19(6):838-856.
[25] CHEN H,CHENG R,WEN J,et al.Solving Large-Scale Many-Objective Optimization Problems by Covariance Matrix Adaptation Evolution Strategy with Scalable Small Subpopulations[J].Information Sciences,2020,509:457-469.
[26] LI B,YANG Y,YANG P,et al.Causal Inference Based Large-Scale Multi-Objective Optimization[J].IEEE Transactions on Evolutionary Computation,2025,29(2):444-458.
[27] LIU S,LIN Q,FENG L,et al.Evolutionary Multitasking for Large-Scale Multiobjective Optimization[J].IEEE Transactions on Evolutionary Computation,2022,27(4):863-877.
[28] LI L,LI Y,LIN Q,et al.Neural Net-Enhanced CompetitiveSwarm Optimizer for Large-Scale Multiobjective Optimization[J].IEEE Transactions on Cybernetics,2023,54(6):3502-3515.
[29] WANG Z,HONG H,YE K,et al.Manifold Interpolation for Large-Scale Multiobjective Optimization via Generative Adversarial Networks[J].IEEE Transactions on Neural Networks and Learning Systems,2021,34(8):4631-4645.
[30] LIANG Z,LI Y,WAN Z.Large Scale Many-Objective Optimization Driven by Distributional Adversarial Networks[J].arXiv:2003.07013,2020.
[31] ARJOVSKY M,CHINTALA S,BOTTOU L.Wasserstein Generative Adversarial Networks[C] //International Conference on Machine Learning.PMLR,2017:214-223.
[32] STORN R,PRICE K.Differential Evolution-A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces[J].Journal of Global Optimization,1997,11:341-359.
[33] CHENG R,JIN Y,OLHOFER M.Test Problems for Large-Scale Multiobjective and Many-Objective Optimization[J].IEEE Transactions on Cybernetics,2016,47(12):4108-4121.
[34] HE C,CHENG R,LI L,et al.Large-scale Multiobjective Optimization via Reformulated Decision Variable Analysis[J].IEEE Transactions on Evolutionary Computation,2022,28(1):47-61.
[35] HE C,CHENG R,ZHANG C,et al.Evolutionary Large-Scale Multiobjective Optimization for Ratio Error Estimation of Voltage Transformers[J].IEEE Transactions on Evolutionary Computation,2020,24(5):868-881.
[36] TIAN Y,CHENG R,ZHANG X,et al.PlatEMO:A MATLAB Platform for Evolutionary Multi-Objective Optimization [Educational Forum] [J].IEEE Computational Intelligence Magazine,2017,12(4):73-87.
[37] ZITZLER E,THIELE L,LAUMANNS M,et al.PerformanceAssessment of Multiobjective Optimizers:An Analysis and Review[J].IEEE Transactions on Evolutionary Computation,2003,7(2):117-132.
[38] ZITZLER E,THIELE L.Multiobjective Evolutionary Algo-rithms:A Comparative Case Study and the Strength Pareto Approach[J].IEEE Transactions on Evolutionary Computation,2002,3(4):257-271.
[39] CHENG R,JIN Y,OLHOFER M,et al.A Reference Vector Guided Evolutionary Algorithm for Many-Objective Optimization[J].IEEE Transactions on Evolutionary Computation,2016,20(5):773-791.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发