Differential evolution with collective ensemble learning

Ensemble learning of multiple search strategies has demonstrated effectiveness in improving the performance of differential evolution (DE) for global optimization. In existing ensemble learning methods, offspring for each target solution is generated by one of the strategies from the strategy pool according to the optimization requirement of the considered problem. However, since the genetic material of an offspring generally comes from one single strategy, the advantages of different strategies could not be simultaneously utilized for optimizing decision variables with different properties. To deal with this problem, this paper proposes the collective ensemble learning (CEL) paradigm, which merges the advantages of multiple strategies for generating an offspring. CEL mainly includes the component decomposition (CD) and component integration (CI) mechanisms. The CD mechanism divides the target solutions and the candidates generated by different generation strategies into exploitative and explorative components respectively, in consideration of the evolution status at the dimension level. Then, the CI mechanism is implemented to integrate the appropriate components to form the offspring according to the sub-similarity measurement performed at the component level. The effectiveness and advantages of CEL have been validated and discussed by performance comparisons with the baseline, each single mechanism, existing ensemble learning methods, as well as several state-of-the-art DE variants.