On the differential evolution schemes in MOEA/D
Waibin Huang, Hui Li · 2010 Sixth International Conference on Natural Computation · 2010
Recently, MOEA/D has gained some success in tackling a class of continuous multi-objective optimization problems with complicated pareto sets. It uses a simple differential evolution scheme (i.e., DE/BEST/1) to produce offspring solutions. However, the performance of MOEA/D is very sensitive to the parameters in differential evolution schemes, such as scaling factor. In this paper, we further investigate the influence of various DE schemes in MOEA/D. Our experimental results show that the performance of MOEA/D relies on the choice of mating parents in DE schemes.