Gradient-Guided Local Search for IGD/IGDPlus Subset Selection
Pages 585 - 593
Abstract
Subset selection is always a hot topic in the community of evolutionary multi-objective optimization (EMO) since it is used in mating selection, environmental selection, and final selection. In the first two scenarios, the task of subset selection algorithms is to select a subset from a small candidate set (e.g., population). However, in the last scenario, it is to select a subset from an unbounded archive with all non-dominated solutions examined during the evolutionary process. Most existing subset selection algorithms aim to improve the hypervolume of subsets (i.e., hypervolume subset selection) selected from the archive. However, only a few researchers work on the IGD and IGD+ (two well-known indicators) subset selection in the last scenario. In this paper, we propose a gradient-guided local search algorithm for IGD/IGD+ subset selection problems. The experimental results show that the proposed algorithm is much faster than the existing lazy greedy inclusion IGD/IGD+ subset selection algorithm, and the quality of the selected subsets is competitive with that selected by the existing greedy algorithms.
References
[1]
Matthieu Basseur, Bilel Derbel, Adrien Goëffon, and Arnaud Liefooghe. 2016. Experiments on greedy and local search heuristics for d-dimensional hypervolume subset selection. In Proc. Genet. Evol. Comput. Conf. Denver Colorado USA, 541--548.
[2]
Peter A. N. Bosman and Dirk Thierens. 2003. The balance between proximity and diversity in multiobjective evolutionary algorithms. IEEE Trans. Evol. Comput. 7, 2 (Apr. 2003), 174--188.
[3]
Lucas Bradstreet, Lyndon While, and Luigi Barone. 2007. Incrementally maximising hypervolume for selection in multi-objective evolutionary algorithms. In Proc. IEEE Congr. Evol. Comput. Singapore, 3203--3210.
[4]
Weiyu Chen, Hisao Ishibuchi, and Ke Shang. 2020. Modified distance-based subset selection for evolutionary multi-objective optimization algorithms. In Proc. IEEE Congr. Evol. Comput. Glasgow, UK, 1--8.
[5]
Weiyu Chen, Hisao Ishibuchi, and Ke Shang. 2021. Clustering-based subset selection in evolutionary multiobjective optimization. In Proc. IEEE Int. Conf. Syst., Man, Cybern.,. Melbourne, Australia, 468--475.
[6]
Weiyu Chen, Hisao Ishibuchi, and Ke Shang. 2022. Fast greedy subset selection from large candidate solution sets in evolutionary multiobjective optimization. IEEE Trans. Evol. Comput. 26, 4 (Aug. 2022), 750--764.
[7]
Indraneel Das and J. E. Dennis. 1998. Normal-bounday intersection: A new method for generating Pareto optimal points in multicriteria optimization problems. SIAM J. Optim. 8, 3 (Aug. 1998), 631--657.
[8]
Hisao Ishibuchi, Hiroyuki Masuda, Yuki Tanigaki, and Yusuke Nojima. 2015. Modified distance calculation in generational distance and inverted generational distance. In Evol. Multi-Criter. Optim. Guimarães, Portugal, 110--125.
[9]
Hisao Ishibuchi, Lie Meng Pang, and Ke Shang. 2020. A new framework of evolutionary multi-objective algorithms with an unbounded external archive. In Proc. Eur. Conf. Artif. Intell. Santiago de Compostela, Spain, 283--290.
[10]
Siwei Jiang, Jie Zhang, Yew-Soon Ong, Allan N. Zhang, and Puay Siew Tan. 2015. A simple and fast hypervolume indicator-based multiobjective evolutionary algorithm. IEEE Trans. Evol. Comput. 45, 10 (Oct. 2015), 2202--2213.
[11]
Yang Nan, Ke Shang, Hisao Ishibuchi, and Linjun He. 2021. Improving local search hypervolume subset selection in evolutionary multi-objective optimization. In Proc. IEEE Int. Conf. Syst., Man, Cybern.,. Melbourne, Australia, 751--757.
[12]
Yang Nan, Ke Shang, Hisao Ishibuchi, and Linjun He. 2023. An improved local search method for large-scale hypervolume subset selection. IEEE Trans. Evol. Comput. 27, 6 (Dec. 2023), 1690--1704.
[13]
Serpil Sayın. 2000. Measuring the quality of discrete representations of efficient sets in multiple objective mathematical programming. Math. Program. 87 (May 2000), 543--560.
[14]
Ke Shang, Hisao Ishibuchi, and Yang Nan. 2021. Distance-based subset selection revisited. In Proc. Genet. Evol. Comput. Conf. Lille France, 439--447.
[15]
Ke Shang, Tianye Shu, Hisao Ishibuchi, Yang Nan, and Lie Meng Pang. 2023. Benchmarking large-scale subset selection in evolutionary multi-objective optimization. Infor. Sci. 622 (Apr. 2023), 755--770.
[16]
Hemant Kumar Singh, Kalyan Shankar Bhattacharjee, and Tapabrata Ray. 2019. Distance-based subset selection for benchmarking in evolutionary multi/many-objective optimization. IEEE Trans. Evol. Comput. 23, 5 (Oct. 2019), 904--912.
[17]
Tamara Ulrich and Lothar Thiele. 2012. Bounding the effectiveness of hypervolume-based (+)-archiving algorithms. In Proc. Int. Conf. Learn. Intell. Optim. Paris, France, 235--249.
[18]
Eckart Zitzler and Lothar Thiele. 1999. Multiobjective evolutionary algorithms: A comparative case study and the strength Pareto approach. IEEE Trans. Evol. Comput. 3, 4 (Nov. 1999), 257--271.
Index Terms
- Gradient-Guided Local Search for IGD/IGDPlus Subset Selection
Recommendations
Analysis of Real-World Constrained Multi-Objective Problems and Performance Comparison of Multi-Objective Algorithms
GECCO '24: Proceedings of the Genetic and Evolutionary Computation ConferenceReal-world multi-objective optimization problems usually have multiple constraints. To solve constrained multi-objective optimization problems (CMOPs), researchers have proposed various evolutionary multi-objective optimization (EMO) algorithms with ...
Comparison of Hypervolume, IGD and IGD+ from the Viewpoint of Optimal Distributions of Solutions
Evolutionary Multi-Criterion OptimizationAbstractHypervolume (HV) and inverted generational distance (IGD) have been frequently used as performance indicators to evaluate the quality of solution sets obtained by evolutionary multiobjective optimization (EMO) algorithms. They have also been used ...
Effects of Objective Space Normalization in Multi-Objective Evolutionary Algorithms on Real-World Problems
GECCO '23: Proceedings of the Genetic and Evolutionary Computation ConferenceIn real-world multi-objective problems, each objective has a totally different scale. However, some frequently-used multi-objective evolutionary algorithms (MOEAs) have no objective space normalization mechanisms. The effect of objective space ...
Comments
Information & Contributors
Information
Published In
July 2024
1657 pages
Copyright © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 14 July 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- the National Key R&D Program of China
- National Natural Science Foundation of China
- Guangdong Provincial Key Laboratory
Conference
GECCO '24
Sponsor:
GECCO '24: Genetic and Evolutionary Computation Conference
July 14 - 18, 2024
VIC, Melbourne, Australia
Acceptance Rates
Overall Acceptance Rate 1,669 of 4,410 submissions, 38%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 58Total Downloads
- Downloads (Last 12 months)58
- Downloads (Last 6 weeks)9
Reflects downloads up to 28 Feb 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in