University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Heterogeneous Ensemble-Based Infill Criterion for Evolutionary Multiobjective Optimization of Expensive Problems

Guo, Dan, Jin, Yaochu, Ding, Jinliang and Chai, Tianyou (2018) Heterogeneous Ensemble-Based Infill Criterion for Evolutionary Multiobjective Optimization of Expensive Problems IEEE Transactions on Cybernetics.

[img]
Preview
Text
Heterogeneous Ensemble Based Infill Criterion for Evolutionary Multi-objective Optimization of Expensive Problems.pdf - Accepted version Manuscript

Download (478kB) | Preview

Abstract

Gaussian processes are the most popular model used in surrogate-assisted evolutionary optimization of computationally expensive problems, mainly because Gaussian processes are able to measure the uncertainty of the estimated fitness values, based on which certain infill sampling criteria can be used to guide the search and update the surrogate model. However, the computation time for constructing Gaussian processes may become excessively long when the number of training samples increases, which makes it inappropriate to use them as surrogates in evolutionary optimization. To address this issue, this paper proposes to use ensembles as surrogates and infill criteria for model management in evolutionary optimization. A heterogeneous ensemble consisting of a least square support vector machine and two radial basis function networks is constructed to enhance the reliability of ensembles for uncertainty estimation. In addition to the original decision variables, a selected subset of the decision variables and a set of transformed variables are used as inputs of the heterogeneous ensemble to further promote the diversity of the ensemble. The proposed heterogeneous ensemble is compared with a Gaussian process and a homogeneous ensemble for infill sampling criteria in evolutionary multi-objective optimization. Experimental results demonstrate that the heterogeneous ensemble is competitive in performance compared with Gaussian processes and much more scalable in computational complexity to the increase in search dimension.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Computing Science
Authors :
NameEmailORCID
Guo, Dan
Jin, YaochuYaochu.Jin@surrey.ac.uk
Ding, Jinliang
Chai, Tianyou
Date : 2018
Identification Number : 10.1109/TCYB.2018.2794503
Copyright Disclaimer : © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Uncontrolled Keywords : Multi-objective optimization; Surrogate-assisted evolutionary algorithm; Heterogeneous ensemble; Gaussian process, Feature selection; Feature extraction
Depositing User : Clive Harris
Date Deposited : 16 Jan 2018 16:27
Last Modified : 16 Jul 2018 09:42
URI: http://epubs.surrey.ac.uk/id/eprint/845628

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800