Generating diverse and discriminatory knapsack instances by searching for novelty in variable dimensions of feature-space

Generating new instances via evolutionary methods is commonly used to create new benchmarking data-sets,with a focus on attempting to cover an instance-space as completely as possible. Recent approaches have exploited Quality-Diversity methods to evolve sets of instances that are both diverse and di...

ver descrição completa

Detalhes bibliográficos
Autores: Segredo González, Eduardo Manuel, Marrero Díaz, Alejandro, Hart, Emma, Bossek, Jakob, Neumann, Aneta
Formato: artículo
Fecha de publicación:2023
País:España
Recursos:Universidad de La Laguna (ULL)
Repositorio:RIULL. Repositorio Institucional de la Universidad de La Laguna
OAI Identifier:oai:riull.ull.es:915/40012
Acesso em linha:http://riull.ull.es/xmlui/handle/915/40012
Access Level:acceso abierto
Palavra-chave:Instance generation
Instance-space analysis
Knapsack problem
Novelty search
Evolutionary computation
Descrição
Resumo:Generating new instances via evolutionary methods is commonly used to create new benchmarking data-sets,with a focus on attempting to cover an instance-space as completely as possible. Recent approaches have exploited Quality-Diversity methods to evolve sets of instances that are both diverse and discriminatory with respect to a portfolio of solvers, but these methods can be challenging when attempting to find diversity in a high-dimensional feature-space. Weaddress this issue by training a model based on Principal Component Analysis on existing instances to create a low-dimension projection of the high-dimension feature-vectors, and then apply Novelty Search directly in the new low-dimension space. We conduct experiments to evolve diverse and discriminatory instances of Knapsack Problems, comparing the use of Novelty Search in the original feature-space to using Novelty Search in a low-dimensional projection, and repeat over a given set of dimensions. We find that the methods are complementary: if treated as an ensemble, they collectively provide increased coverage of the space. Specifically, searching for novelty in a low-dimension space contributes 56% of the filled regions of the space, while searching directly in the feature-space covers the remaining 44%.