Balancing Convergence and Diversity in Decomposition-Based Many-Objective Optimizers

Research output: Contribution to journalArticlepeer-review

Standard

Balancing Convergence and Diversity in Decomposition-Based Many-Objective Optimizers. / Yuan, Yuan; Xu, Hua; Wang, Bo; Zhang, Bo; Yao, Xin.

In: IEEE Transactions on Evolutionary Computation, 09.06.2015.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{94f77c127451440a84c31cfe650a9401,
title = "Balancing Convergence and Diversity in Decomposition-Based Many-Objective Optimizers",
abstract = "The decomposition-based multiobjective evolutionary algorithms generally make use of aggregation functions to decompose a multiobjective optimization problem into multiple single-objective optimization problems. However, due to the nature of contour lines for the adopted aggregation functions, they usually fail in preserving the diversity in high-dimensional objective space even by using diverse weight vectors. To address this problem, we propose to maintain the desired diversity of solutions in their evolutionary process explicitly by exploiting the perpendicular distance from the solution to the weight vector in the objective space, which achieves better balance between convergence and diversity in many-objective optimization. The idea is implemented to enhance two well-performing decomposition-based algorithms, i.e., multiobjective evolutionary algorithms based on decomposition and ensemble fitness ranking. The two enhanced algorithms are compared to several state-of the- art algorithms, and a series of comparative experiments are conducted on a number of test problems from two well-known test suites. The experimental results show that the two proposed algorithms are generally more effective than their predecessors in balancing convergence and diversity, and they are also very competitive against other existing algorithms for solving many objective optimization problems.",
author = "Yuan Yuan and Hua Xu and Bo Wang and Bo Zhang and Xin Yao",
year = "2015",
month = jun,
day = "9",
doi = "10.1109/TEVC.2015.2443001",
language = "English",
journal = "IEEE Transactions on Evolutionary Computation",
issn = "1089-778X",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

RIS

TY - JOUR

T1 - Balancing Convergence and Diversity in Decomposition-Based Many-Objective Optimizers

AU - Yuan, Yuan

AU - Xu, Hua

AU - Wang, Bo

AU - Zhang, Bo

AU - Yao, Xin

PY - 2015/6/9

Y1 - 2015/6/9

N2 - The decomposition-based multiobjective evolutionary algorithms generally make use of aggregation functions to decompose a multiobjective optimization problem into multiple single-objective optimization problems. However, due to the nature of contour lines for the adopted aggregation functions, they usually fail in preserving the diversity in high-dimensional objective space even by using diverse weight vectors. To address this problem, we propose to maintain the desired diversity of solutions in their evolutionary process explicitly by exploiting the perpendicular distance from the solution to the weight vector in the objective space, which achieves better balance between convergence and diversity in many-objective optimization. The idea is implemented to enhance two well-performing decomposition-based algorithms, i.e., multiobjective evolutionary algorithms based on decomposition and ensemble fitness ranking. The two enhanced algorithms are compared to several state-of the- art algorithms, and a series of comparative experiments are conducted on a number of test problems from two well-known test suites. The experimental results show that the two proposed algorithms are generally more effective than their predecessors in balancing convergence and diversity, and they are also very competitive against other existing algorithms for solving many objective optimization problems.

AB - The decomposition-based multiobjective evolutionary algorithms generally make use of aggregation functions to decompose a multiobjective optimization problem into multiple single-objective optimization problems. However, due to the nature of contour lines for the adopted aggregation functions, they usually fail in preserving the diversity in high-dimensional objective space even by using diverse weight vectors. To address this problem, we propose to maintain the desired diversity of solutions in their evolutionary process explicitly by exploiting the perpendicular distance from the solution to the weight vector in the objective space, which achieves better balance between convergence and diversity in many-objective optimization. The idea is implemented to enhance two well-performing decomposition-based algorithms, i.e., multiobjective evolutionary algorithms based on decomposition and ensemble fitness ranking. The two enhanced algorithms are compared to several state-of the- art algorithms, and a series of comparative experiments are conducted on a number of test problems from two well-known test suites. The experimental results show that the two proposed algorithms are generally more effective than their predecessors in balancing convergence and diversity, and they are also very competitive against other existing algorithms for solving many objective optimization problems.

U2 - 10.1109/TEVC.2015.2443001

DO - 10.1109/TEVC.2015.2443001

M3 - Article

JO - IEEE Transactions on Evolutionary Computation

JF - IEEE Transactions on Evolutionary Computation

SN - 1089-778X

ER -