Learning to Decompose : A Paradigm for Decomposition-Based Multiobjective Optimization

Mengyuan WU, Ke LI, Sam KWONG, Qingfu ZHANG, Jun ZHANG

Research output: Journal PublicationsJournal Article (refereed)peer-review

92 Citations (Scopus)

Abstract

The decomposition-based evolutionary multiobjective optimization (EMO) algorithm has become an increasingly popular choice for a posteriori multiobjective optimization. However, recent studies have shown that their performance strongly depends on the Pareto front (PF) shapes. This can be attributed to the decomposition method, of which the reference points and subproblem formulation settings are not well adaptable to various problem characteristics. In this paper, we develop a learning-to-decompose (LTD) paradigm that adaptively sets the decomposition method by learning the characteristics of the estimated PF. Specifically, it consists of two interdependent parts, i.e., a learning module and an optimization module. Given the current nondominated solutions from the optimization module, the learning module periodically learns an analytical model of the estimated PF. Thereafter, useful information is extracted from the learned model to set the decomposition method for the optimization module: 1) reference points compliant with the PF shape and 2) subproblem formulations whose contours and search directions are appropriate for the current status. Accordingly, the optimization module, which can be any decomposition-based EMO algorithm in principle, decomposes the multiobjective optimization problem into a number of subproblems and optimizes them simultaneously. To validate our proposed LTD paradigm, we integrate it with two decomposition-based EMO algorithms, and compare them with four state-of-the-art algorithms on a series of benchmark problems with various PF shapes.

Original languageEnglish
Article number8439014
Pages (from-to)376-390
Number of pages15
JournalIEEE Transactions on Evolutionary Computation
Volume23
Issue number3
Early online date17 Aug 2018
DOIs
Publication statusPublished - Jun 2019
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 1997-2012 IEEE.

Funding

This work was supported in part by the Hong Kong Research Grants Council (RGC) General Research Fund under Grant 9042038 (CityU 11205314), in part by the ANR/RCC Joint Research Scheme through the Hong Kong RGC and the France National Research Agency under Project A-CityU101/16, in part by the Royal Society under Grant IEC/NSFC/170243, and in part by the Chinese National Science Foundation of China under Grant 61672443 and Grant 61473241.

Keywords

  • Decomposition
  • evolutionary computation
  • Gaussian process (GP) regression
  • multiobjective optimization
  • reference points generation

Fingerprint

Dive into the research topics of 'Learning to Decompose : A Paradigm for Decomposition-Based Multiobjective Optimization'. Together they form a unique fingerprint.

Cite this