.png){kind=icon}
返回
A fast sampling based evolutionary algorithm for million-dimensional multiobjective optimization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.swevo.2022.101181.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
With their complexity and vast search space, large-scale multiobjective optimization problems (LSMOPs) challenge existing multiobjective evolutionary algorithms (MOEAs). Recently, several large-scale multiobjective evolutionary algorithms have been developed to tackle LSMOPs. Unlike conventional MOEAs that concentrate on selection operations in the objective space, large-scale MOEAs emphasize operations in the decision space, such as offspring generation, to tackle the large number of decision variables. Nevertheless, most present large-scale MOEAs experience difficulty effectively and efficiently solving LSMOPs with tens of thousands or more decision variables or exhibit poor versatility in solving different LSMOPs. We propose a fast large-scale MOEA framework with reference-guided offspring generation, named FLEA, aiming at these issues. Generally, FLEA constructs several reference vectors in the decision space to steer the sampling of promising solutions during offspring generation. A parameter is used to allocate computation resources between the convergence and diversity of the offspring population adaptively. Without computationally expensive problem reformulation or decision variable analysis techniques, the proposed method can significantly accelerate the search speed of conventional MOEAs in solving LSMOPs. FLEA is examined on various LSMOPs with up to 1.6 million decision variables, demonstrating its superior effectiveness, efficiency, and versatility in large-scale multiobjective optimization.
Keyword:
Evolutionary algorithm
Multiobjective optimization
Offspring generation
Large-scale optimization
Reference vector
期刊
IF:
8.5
论文数:
2.2K
被引数:
1.0W
机构
引用论文
A survey on swarm intelligence approaches to feature selection in data mining数据挖掘中特征选择的群体智能方法综述
.png){kind=icon}
PREAI
分享收藏PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective OptimizationPlatEMO: 用于进化多目标优化的MATLAB平台
OAAI
OAAI分享收藏A two-stage evolutionary algorithm for large-scale sparse multiobjective optimization problems求解大规模稀疏多目标优化问题的两阶段进化算法
PREAI
分享收藏ME-MEOA/Dcc : Multiobjective constrained clustering through decomposition-based memetic elitism
PREAI
分享收藏Multimodal Optimization Enhanced Cooperative Coevolution for Large-Scale Optimization用于大规模优化的多模式优化增强的合作协同进化
PREAI
分享收藏分享收藏A Strengthened Dominance Relation Considering Convergence and Diversity for Evolutionary Many-Objective Optimization进化多目标优化中考虑收敛性和多样性的增强优势关系OAAI
OAAI分享收藏
查看更多内容