Multi-objective evolutionary multitasking algorithm based on cross-task transfer solution matching strategy

The superior performance of evolutionary multitasking (EMT) algorithms is largely owing to the potential synergy between tasks. Current EMT algorithms only involve a unidirectional process of transferring individuals from the source task to the target task. This method does not consider the search preference of the target task in the process of finding transferred individuals; therefore, the potential synergy between tasks is not fully utilized. Herein, we propose a bidirectional knowledge transfer method, which refers to the search preference of the target task in the process of finding transferred individuals. These transferred individuals fit the search process well for the target task. In addition, an adaptive strategy for adjusting the intensity of the knowledge transfer is proposed. This method enables the algorithm to adjust the intensity of knowledge transfer independently according to the living conditions of the individuals to be transferred to balance the convergence of the population with the computational intensity of the algorithm. The proposed algorithm is compared with comparison algorithms on 38 multi-objective multitasking optimization benchmarks. Experimental results show that the proposed algorithm is not only outperforming other comparison algorithms in more than 30 benchmarks, but also has considerable convergence efficiency.