Performance of Decomposition-Based Many-Objective Algorithms Strongly Depends on Pareto Front Shapes

By Hisao Ishibuchi, Yu Setoguchi, Hiroyuki Masuda, Yusuke Nojima. IEEE Transactions on Evolutionary Computation, 2017

503 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

View Paper: https://www.semanticscholar.org/paper/b8aedaecbd302874049c18f077c412f75f3f2f33

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yaochu Jin
2. Xing-yi Zhang
3. Ye Tian
4. Ran Cheng
5. Handing Wang
6. Yanan Sun
7. Gary G. Yen
8. Hisao Ishibuchi

In Computational Theory and Mathematics

1. Yaochu Jin
2. Xing-yi Zhang
3. Ye Tian
4. Ran Cheng
5. Yanan Sun
6. Gary G. Yen
7. Handing Wang
8. Xiutao Zheng

Citations in the corpus

• A Survey of Multiobjective Evolutionary Algorithms Based on Decomposition (2017, methodology): “problem is such that there are some reference points which have no P-O solution associated with them [84], [124].”
• Data-Driven Evolutionary Optimization: An Overview and Case Studies (2019, background): “The effect of parameters on performance metrics has been analyzed in details in [88] and [89].”
• PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimization [Educational Forum] (2017, methodology): “Afterwards, the evolutionary algorithm based on decomposition (MOEA/D) was proposed in 2007 [17], and som e ther MOEAs following the basic idea of MOEA/D had also been developed since then [18]–[21].”
• Improved Regularity Model-Based EDA for Many-Objective Optimization (2018, methodology): “To this end, the DTLZ1−1-DTLZ4−1 problems from the DTLZ−1 test suit, which is a variant of the DTLZ by multiplying the negative sign to each test problem in DTLZ, are included into the considered benchmark test problems for their more complicated PF shapes which especially challenges algorithms base”
• An easy-to-use real-world multi-objective optimization problem suite (2020, methodology): “While recently proposed EMOAs perform well on problems with many objectives, they lack the ability to handle problems with irregular Pareto fronts [12, 47].”
• Efficient Large-Scale Multiobjective Optimization Based on a Competitive Swarm Optimizer (2020, background): “In addition, the environmental selection of the proposed LMOCSO is based on a set of reference vectors, which are overspecialized for the MOPs with regular Pareto fronts [68].”
• A Strengthened Dominance Relation Considering Convergence and Diversity for Evolutionary Many-Objective Optimization (2018, background): “Despite that existing dominance relations can enhance selection pressure for MOEAs in solving MaOPs, as shown in [7], [8], and [30], most of the dominance relations can only find a set of solutions concentrating on a small region of the Pareto front.”
• An Indicator-Based Multiobjective Evolutionary Algorithm With Reference Point Adaptation for Better Versatility (2018, background): “[28], good results can be obtained by these algorithms only if the distribution of weight vectors is consistent with the Pareto”