Coevolutionary Pareto Diversity Optimization

TL;DR

This paper introduces a coevolutionary Pareto Diversity Optimization method that reformulates constrained problems as bi-objective problems, enhancing solution diversity and quality through co-evolution and crossover techniques.

Contribution

The paper presents a novel coevolutionary Pareto-based approach for diversity optimization, outperforming existing algorithms like DIVEA and exploring improvements such as inter-population crossover.

Findings

Outperforms DIVEA in solution diversity and quality

Inter-population crossover further enhances diversity

Bi-objective reformulation effectively maintains high-quality diverse solutions

Abstract

Computing diverse sets of high quality solutions for a given optimization problem has become an important topic in recent years. In this paper, we introduce a coevolutionary Pareto Diversity Optimization approach which builds on the success of reformulating a constrained single-objective optimization problem as a bi-objective problem by turning the constraint into an additional objective. Our new Pareto Diversity optimization approach uses this bi-objective formulation to optimize the problem while also maintaining an additional population of high quality solutions for which diversity is optimized with respect to a given diversity measure. We show that our standard co-evolutionary Pareto Diversity Optimization approach outperforms the recently introduced DIVEA algorithm which obtains its initial population by generalized diversifying greedy sampling and improving the diversity of the set of solutions afterwards. Furthermore, we study possible improvements of the Pareto Diversity Optimization approach. In particular, we show that the use of inter-population crossover further improves the diversity of the set of solutions.