Many-Objective Optimization for Knapsack Problems Using Correlation-Based Weighted Sum Approach

  • Authors:

  • Tadahiko Murata;Akinori Taki

  • Affiliations:

  • Department of Informatics, Kansai University, Osaka, Japan 569-1073 and Policy Grid Computing Laboratory, Institute for Socionetwork Strategies, Kansai University, Osaka, Japan 564-8680;Graduate School of Informatics, Kansai University, Osaka, Japan 569-1073

  • Venue:
  • EMO '09 Proceedings of the 5th International Conference on Evolutionary Multi-Criterion Optimization
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we examine the effectiveness of an EMO (Evolutionary Multi-criterion Optimization) algorithm using a correlation based weighted sum for many objective optimization problems. Recently many EMO algorithms are proposed for various multi-objective problems. However, it is known that the convergence performance to the Pareto-frontier becomes weak in approaches using archives for non-dominated solutions since the size of archives becomes large as the number of objectives becomes large. In this paper, we show the effectiveness of using a correlation information between objectives to construct groups of objectives. Our simulation results show that while an archive-based approach, such as NSGA-II, produces a set of non-dominated solutions with better objective values in each objective, the correlation-based weighted sum approach can produce better compromise solutions that has averagely better objective values in every objective.