Transfer Learning Based Co-Surrogate Assisted Evolutionary Bi-Objective Optimization for Objectives with Non-Uniform Evaluation Times.

Autor: Wang X; Department of Computer Science, University of Surrey, Guildford, GU2 7XH, United Kingdom xilu.wang@surrey.ac.uk., Jin Y; Faculty of Technology, Bielefeld University, D-33615 Bielefeld, Germany.; Department of Computer Science, University of Surrey, Guildford, GU2 7XH, United Kingdom yaochu.jin@uni-bielefeld.de., Schmitt S; Honda Research Institute Europe GmbH, Carl-Legien-Strasse 30, D-63073 Offenbach/Main, Germany sebastian.schmitt@honda-ri.de., Olhofer M; Honda Research Institute Europe GmbH, Carl-Legien-Strasse 30, D-63073 Offenbach/Main, Germany markus.olhofer@honda-ri.de.
Jazyk: angličtina
Zdroj: Evolutionary computation [Evol Comput] 2022 Jun 01; Vol. 30 (2), pp. 221-251.
DOI: 10.1162/evco_a_00300
Abstrakt: Most existing multiobjective evolutionary algorithms (MOEAs) implicitly assume that each objective function can be evaluated within the same period of time. Typically. this is untenable in many real-world optimization scenarios where evaluation of different objectives involves different computer simulations or physical experiments with distinct time complexity. To address this issue, a transfer learning scheme based on surrogate-assisted evolutionary algorithms (SAEAs) is proposed, in which a co-surrogate is adopted to model the functional relationship between the fast and slow objective functions and a transferable instance selection method is introduced to acquire useful knowledge from the search process of the fast objective. Our experimental results on DTLZ and UF test suites demonstrate that the proposed algorithm is competitive for solving bi-objective optimization where objectives have non-uniform evaluation times.
(© 2021 Massachusetts Institute of Technology.)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje