Behavior of Evolutionary Many-Objective Optimization

Evolutionary multiobjective optimization (EMO) is one of the most active research areas in the field of evolutionary computation. Whereas EMO algorithms have been successfully used in various application tasks, it has also been reported that they do not work well on many-objective problems. In this paper, first we examine the behavior of the most well-known and frequently-used EMO algorithm on many-objective 0/1 knapsack problems. Next we briefly review recent proposals for the scalability improvement of EMO algorithms to many-objective problems. Then their effects on the search ability of EMO algorithms are examined. Experimental results show that the increase in the convergence of solutions to the Pareto front often leads to the decrease in their diversity. Based on this observation, we suggest future research directions in evolutionary many-objective optimization.