Revisiting the NSGA-II crowding-distance computation

Abstract

This paper improves upon the reference NSGA-II procedure by removing an instability in its crowding distance operator. This instability stems from the cases where two or more individuals on a Pareto front share identical fitnesses. In those cases, the instability causes their crowding distance to either become null, or to depend on the individual's position within the Pareto front sequence. Experiments conducted on nine different benchmark problems show that, by computing the crowding distance on unique fitnesses instead of individuals, both the convergence and diversity of NSGA-II can be significantly improved.

DOI: 10.1145/2463372.2463456

Extracted Key Phrases

12 Figures and Tables

Cite this paper

@inproceedings{Fortin2013RevisitingTN, title={Revisiting the NSGA-II crowding-distance computation}, author={F{\'e}lix-Antoine Fortin and Marc Parizeau}, booktitle={GECCO}, year={2013} }