On the Unbounded External Archive and Population Size in Preference-based Evolutionary Multi-objective Optimization Using a Reference Point

被引:2
|
作者
Tanabe, Ryoji [1 ]
机构
[1] Yokohama Natl Univ, Yokohama, Kanagawa, Japan
关键词
Preference-based evolutionary multi-objective optimization; unbounded external archive; population size; benchmarking; ALGORITHM; DOMINANCE; SELECTION; MOEA/D;
D O I
10.1145/3583131.3590511
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Although the population size is an important parameter in evolutionary multi-objective optimization (EMO), little is known about its influence on preference-based EMO (PBEMO). The effectiveness of an unbounded external archive (UA) in PBEMO is also poorly understood, where the UA maintains all non-dominated solutions found so far. In addition, existing methods for postprocessing the UA cannot handle the decision maker's preference information. In this context, first, this paper proposes a preference-based postprocessing method for selecting representative solutions from the UA. Then, we investigate the influence of the UA and population size on the performance of PBEMO algorithms. Our results show that the performance of PBEMO algorithms (e.g., R-NSGA-II) can be significantly improved by using the UA and the proposed method. We demonstrate that a smaller population size than commonly used is effective in most PBEMO algorithms for a small budget of function evaluations, even for many objectives. We found that the size of the region of interest is a less important factor in selecting the population size of the PBEMO algorithms on real-world problems.
引用
收藏
页码:749 / 758
页数:10
相关论文
共 50 条
  • [41] A preference-based multi-objective demand response mechanism
    Santos da Silva, Igor Rafael
    Almeida de Alencar, Jose Eduardo
    Lira Rabelo, Ricardo de Andrade
    2020 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2020,
  • [42] Reference point based evolutionary multi-objective optimization algorithms with convergence properties using KKTPM and ASF metrics
    Mohamed Abouhawwash
    Kalyanmoy Deb
    Journal of Heuristics, 2021, 27 : 575 - 614
  • [43] Reference point based evolutionary multi-objective optimization algorithms with convergence properties using KKTPM and ASF metrics
    Abouhawwash, Mohamed
    Deb, Kalyanmoy
    JOURNAL OF HEURISTICS, 2021, 27 (04) : 575 - 614
  • [44] A Preference Based Interactive Evolutionary Algorithm for Multi-objective Optimization: PIE
    Sindhya, Karthik
    Ruiz, Ana Belen
    Miettinen, Kaisa
    EVOLUTIONARY MULTI-CRITERION OPTIMIZATION, 2011, 6576 : 212 - +
  • [45] Multi-objective evolutionary algorithm based on preference for constrained optimization problems
    Dong, Ning
    Wang, Yuping
    Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian University, 2014, 41 (01): : 98 - 104
  • [46] Reference Point-based Evolutionary Multi-objective Optimization for Reversible Logic Circuit Synthesis
    Wang, Xiaoxiao
    Wang, Xiaoxiao
    2014 7TH INTERNATIONAL CONFERENCE ON BIOMEDICAL ENGINEERING AND INFORMATICS (BMEI 2014), 2014, : 955 - 959
  • [47] Reference point based evolutionary multi-objective optimization with dynamic resampling for production systems improvement
    Ng A.H.C.
    Siegmund F.
    Deb K.
    Ng, Amos H.C. (amos.ng@his.se), 2018, Emerald Group Holdings Ltd. (20) : 489 - 512
  • [48] An approach to evolutionary multi-objective optimization algorithm with preference
    Wang, JW
    Zhang, Q
    Zhang, HM
    Wei, XP
    Proceedings of 2005 International Conference on Machine Learning and Cybernetics, Vols 1-9, 2005, : 2966 - 2970
  • [49] Desirable Objective Ranges in Preference-Based Evolutionary Multiobjective Optimization
    Gonzalez-Gallardo, Sandra
    Saborido, Ruben
    Ruiz, Ana B.
    Luque, Mariano
    APPLICATIONS OF EVOLUTIONARY COMPUTATION, EVOAPPLICATIONS 2021, 2021, 12694 : 227 - 241
  • [50] A multi-objective particle swarm optimizer based on reference point for multimodal multi-objective optimization
    Li, Guosen
    Zhou, Ting
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2022, 107