Progressively Adding Objectives: A Case Study in Anomaly Detection

Luis Martí 1, 2 Arsene Fansi-Tchango 3 Laurent Navarro 3 Marc Schoenauer 4, 1
1 TAU - TAckling the Underspecified
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : One of the principles of evolutionary multi-objective optimization is the conjoint optimization of the objective functions. However, in some cases, some of the objectives are easier to attain than others. This causes the population to lose diversity at a high rate and stagnate in early stages of the evolution. This paper presents the progressive addition of objectives (PAO) heuristic. PAO gradually adds objectives to a given problem relying on a perceived measure of complexity. This diversity loss phenomenon caused by the nature of a given objective has been observed when applying the Voronoi diagram-based evolutionary algorithm (VorEAl) in anomaly detection problems. Consequently, PAO has been first directed to address that issue. e experimental studies carried out show that the PAO heuristic manages to yield be er results than the direct use of VorEAl on a group of test problems.
Complete list of metadatas

https://hal.inria.fr/hal-01525611
Contributor : Luis Martí <>
Submitted on : Wednesday, May 31, 2017 - 5:05:13 AM
Last modification on : Thursday, February 7, 2019 - 3:46:38 PM
Long-term archiving on : Wednesday, September 6, 2017 - 10:03:49 AM

Files

main-sigconf.pdf
Publisher files allowed on an open archive

Identifiers

Citation

Luis Martí, Arsene Fansi-Tchango, Laurent Navarro, Marc Schoenauer. Progressively Adding Objectives: A Case Study in Anomaly Detection. Genetic and Evolutionary Computation Conference (GECCO 2017), Jul 2017, Berlin, Germany. ⟨10.1145/3071178.3071333⟩. ⟨hal-01525611⟩

Share

Metrics

Record views

477

Files downloads

229