Abstract
There exist many multi-objective optimization problems (MOPs) containing a large number of decision variables in real-world applications, which are known as large-scale MOPs. Due to the ineffectiveness of existing operators in finding optimal solutions in a huge decision space, some decision variable division based algorithms have been tailored for improving the search efficiency in solving large-scale MOPs. However, these algorithms will encounter difficulties when solving problems with complicated landscapes, as the decision variable division is likely to be inaccurate and time-consuming. In this paper, we propose a competitive swarm optimizer (CSO) based efficient search for solving large-scale MOPs. The proposed algorithm adopts a new particle updating strategy that suggests a twostage strategy to update position, which can highly improve the search efficiency. Experimental results on large-scale benchmark MOPs and an application example demonstrate the superiority of the proposed algorithm over several state-of-the-art multi-objective evolutionary algorithms, including problem transformation based algorithm, decision variable clustering based algorithm, particle swarm optimization algorithm, and estimation of distribution algorithm.