Book Chapter10.1007/978-3-319-13356-0_35
A Novel Evolutionary Multi-objective Algorithm Based on S Metric Selection and M2M Population Decomposition
Lei Chen,Hai-Lin Liu,Chuan Lu,Chuan Lu,Yiu-ming Cheung,Jun Zhang +5 more
- 01 Jan 2015
- pp 441-452
6
TL;DR: A novel S metric selection evolutionary algorithm based on the population decomposition strategy MOEA/D-M2M is proposed to give a simple but effective method to improve the effectiveness of SMS based algorithm.
read more
Abstract: The excellent performance of evolutionary multi-objective algorithms based on S metric selection (SMS) has been identified by many researchers. However, huge computational effort of S metric calculation has limited the full application of those algorithms. This paper proposes a novel S metric selection evolutionary algorithm (SMS-M2M) based on the population decomposition strategy MOEA/D-M2M. In SMS-M2M, SMS is conducted in each subpopulation instead of the whole population, which can avoid the S metric calculation of the total population. The purpose of population decomposition is to directly reduce the huge computational effort of calculating S metric and thus to give a simple but effective method to improve the effectiveness of SMS based algorithm. SMS-M2M utilizes the same SMS with a popular SMS based evolutionary algorithm SMS-EMOA. Numerical studies of SMS-M2M and SMS-EMOA have shown that the M2M population decomposition can effectively reduce the computational effort of SMS, meanwhile the theoretic analysis identifies the efficiency and effectiveness of SMS-M2M.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Reference Vector Guided Evolutionary Algorithm for Many-Objective Optimization
TL;DR: In the proposed algorithm, a scalarization approach, termed angle-penalized distance, is adopted to balance convergence and diversity of the solutions in the high-dimensional objective space, and reference vectors are effective and cost-efficient for preference articulation, which is particularly desirable for many-objective optimization.
1.5K
Preference-Inspired Co-Evolutionary Algorithms With Local PCA Oriented Goal Vectors for Many-Objective Optimization
Zhe Shu,Weiping Wang +1 more
TL;DR: An improved PICEA-g is proposed to further resolve this long-standing problem and could have good performance on most of the test suites assessed in this research, and it performs very well compared with other many-objective optimization algorithms.
6
Combining modified inverted generational distance indicator with reference-vector-guided selection for many-objective optimization
TL;DR: A two-stage selection mechanism uses the IGD^+ indicator and the reference vector guidance method to select two sub-populations, which form the parent population at the next generation when solving MaOPs.
6
Preference-inspired coevolutionary algorithm with sparse autoencoder for many-objective optimization
Wei Wang,Shanxin Zhang,Wei-an Song,Wenlong Ge +3 more
TL;DR: The preference-inspired coevolutionary algorithm with sparse autoencoder (PICEA-g/SAE) is evaluated by three widely used benchmark suites and compared with nine classic multi-objective evolutionary algorithms to prove the advantages of the sparse aut Koencoder framework.
2
Adaptive stochastic fractal search algorithm for multi-objective optimization
HongShang Xu,Bei Dong,Xiaochang Liu,Ming Lei,Xiaojun Wu +4 more
TL;DR: This paper proposes RVSFS, a reference vector-guided stochastic fractal search algorithm for multi-objective optimization, which balances exploration and exploitation using adaptive mechanisms, Gaussian walks, and Levy flights, outperforming five state-of-the-art algorithms on 45 benchmarks.
1
References
A unified model for multi-objective evolutionary algorithms with elitism
Marco Laumanns,Eckart Zitzler,Lothar Thiele +2 more
- 16 Jul 2000
TL;DR: A unified model of multi-objective evolutionary algorithms, in which arbitrary variation and selection operators can be combined as building blocks, including archiving and re-insertion strategies is presented.