An Autoencoder-embedded Evolutionary Optimization Framework for High-dimensional Problems

Document Type

Conference Proceeding

Publication Date

10-11-2020

Abstract

Many ever-increasingly complex engineering optimization problems fall into the class of High-dimensional Expensive Problems (HEPs), where fitness evaluations are very time-consuming. It is extremely challenging and difficult to produce promising solutions in high-dimensional search space. In this paper, an Autoencoder-embedded Evolutionary Optimization (AEO) framework is proposed for the first time. As an efficient dimension reduction tool, an autoencoder is used to compress high-dimensional landscape to informative low-dimensional space. The search operation in this low-dimensional space can facilitate the population converge towards the optima more efficiently. To balance the exploration and exploitation ability during optimization, two sub-populations coevolve in a distributed fashion, where one is assisted by an autoencoder and the other undergoes a regular evolutionary process. The information between these two sub-populations are dynamically exchanged. The proposed algorithm is validated by testing several 200 dimensional benchmark functions. Compared with the state-of-art algorithms for HEPs, AEO shows extraordinarily high efficiency for these challenging problems.

Identifier

85098892129 (Scopus)

ISBN

[9781728185262]

Publication Title

Conference Proceedings IEEE International Conference on Systems Man and Cybernetics

External Full Text Location

https://doi.org/10.1109/SMC42975.2020.9282964

ISSN

1062922X

First Page

1046

Last Page

1051

Volume

2020-October

Grant

2018YFB1305304

Fund Ref

National Natural Science Foundation of China

This document is currently not available here.

Share

COinS