A Study on Knowledge Reuse Strategies in Multitasking Differential Evolution

Chen Jin, Pei-Wei Tsai, A. Kai Qin

Abstract: Evolutionary multi-task optimization (EMTO) is a newly emerging research area which studies on how to solve multiple optimization problems simultaneously using evolutionary algorithms (EAs) so that useful knowledge (e.g. promising candidate solutions) obtained when solving one task can be transferred and reused to facilitate solving some other tasks. In EMTO, how to effectively transfer and reuse knowledge among multiple tasks is an important subject of study. Among existing EMTO techniques, DE-based EMTO algorithms deserve special attention because DE, as one of the most popular EAs, has achieved remarkable feats for solving challenging (single-task) optimization problems in the past although DE-based EMTO is not yet extensively studied. In this paper, we propose a general multitasking DE (MTDE) framework which aims to help more clearly understand the focuses and differences of existing and potential works on DE-based EMTO. We implement this framework via three commonly-used DE search schemes and perform a thorough empirical study on two DE-specific knowledge reuse strategies which are based upon base and differential vectors, respectively. Experiments on 18 MTO demonstrate that the base vector based knowledge reuse strategy outperforms the differential vector based one across all three tested DE search schemes.