Evolutionary Computation for Large-scale Multi-objective Optimization: A Decade of Progresses

Abstract Large-scale multi-objective optimization problems (MOPs) that involve a large number of decision variables, have emerged from many real-world applications. While evolutionary algorithms (EAs) been widely acknowledged as mainstream method for MOPs, most research progress and successful applications EAs restricted to MOPs with small-scale variables. More recently, it has reported traditional (MOEAs) suffer severe deterioration the increase As result, motivated by emergence large-scale investigation MOEAs in this aspect attracted much more attention past decade. This paper reviews computation two angles. From key difficulties scalability analysis is discussed focusing on performance existing challenges induced perspective methodology, are categorized into three classes introduced respectively: divide conquer based, dimensionality reduction based enhanced search-based approaches. Several future directions also discussed.