Effects of Objective Space Normalization in Multi-Objective Evolutionary Algorithms on Real-World Problems
Pages 670 - 678
Abstract
In 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 normalization on the performance of decomposition-based MOEAs (e.g., MOEA/D and NSGA-III) has already been examined for artificial test problems (e.g., DTLZ and WFG) in the literature. In this paper, we examine its practical usefulness for real-world multi-objective problems using various MOEAs. Our experimental results clearly show that objective space normalization is needed not only in decomposition-based MOEAs but also in hypervolume-based MOEAs. We also explain why objective space normalization is needed in these two types of MOEAs.
References
[1]
Nicola Beume, Boris Naujoks, and Michael Emmerich. 2007. SMS-EMOA: Multiobjective selection based on dominated hypervolume. European Journal of Operational Research 181, 3 (Sept. 2007), 1653--1669.
[2]
Julian Blank, Kalyanmoy Deb, and Proteek Chandan Roy. 2019. Investigating the normalization procedure of NSGA-III. In Proceedings of Evolutionary Multi-Criterion Optimization, Vol. 11411. East Lansing, MI, USA, 229--240.
[3]
Lei Chen, Kalyanmoy Deb, Hai-Lin Liu, and Qingfu Zhang. 2020. Effect of objective normalization and penalty parameter on penalty boundary intersection decomposition based evolutionary many-objective optimization algorithms. Evolutionary Computation (June 2020), 1--25.
[4]
Ran Cheng, Yaochu Jin, Markus Olhofer, and Bernhard Sendhoff. 2016. A reference vector guided evolutionary algorithm for many-objective optimization. IEEE Transactions on Evolutionary Computation 20, 5 (Oct. 2016), 773--791.
[5]
Kalyanmoy Deb and Himanshu Jain. 2014. An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part I: Solving problems with box constraints. IEEE Transactions on Evolutionary Computation 18, 4 (Aug. 2014), 577--601.
[6]
K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan. 2002. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation 6, 2 (April 2002), 182--197.
[7]
Kalyanmoy Deb, Lothar Thiele, Marco Laumanns, and Eckart Zitzler. 2002. Scalable multi-objective optimization test problems. In Proceedings of the IEEE Congress on Evolutionary Computation. Honolulu, USA, 825--830.
[8]
Hiroaki Fukumoto and Akira Oyama. 2019. Impact of estimation method of ideal/nadir points on practically-constrained multi-objective optimization problems for decomposition-based multi-objective evolutionary algorithm. In IEEE Symposium Series on Computational Intelligence. Xiamen, China, 2138--2145.
[9]
Cheng He, Ye Tian, Handing Wang, and Yaochu Jin. 2020. A repository of real-world datasets for data-driven evolutionary multiobjective optimization. Complex & Intelligent Systems 6, 1 (2020), 189--197.
[10]
Linjun He, Hisao Ishibuchi, and Dipti Srinivasan. 2021. Metric for evaluating normalization methods in multiobjective optimization. In Proceedings of the Genetic and Evolutionary Computation Conference. Lille, France, 403--411.
[11]
Linjun He, Hisao Ishibuchi, Anupam Trivedi, and Dipti Srinivasan. 2020. Dynamic normalization in MOEA/D for multiobjective optimization. In Proceedings of the IEEE Congress on Evolutionary Computation. Glasgow, Scotland, United Kingdom.
[12]
Linjun He, Yang Nan, Ke Shang, and Hisao Ishibuchi. 2019. A study of the naïve objective space normalization method in MOEA/D. In IEEE Symposium Series on Computational Intelligence. Xiamen, China, 1834--1840.
[13]
Linjun He, Ke Shang, and Hisao Ishibuchi. 2020. Simultaneous use of two normalization methods in decomposition-based multi-objective evolutionary algorithms. Applied Soft Computing 92 (July 2020).
[14]
Linjun He, Ke Shang, Yang Nan, Hisao Ishibuchi, and Dipti Srinivasan. 2022 (Early Access). Relation Between Objective Space Normalization and Weight Vector Scaling in Decomposition-Based Multi-Objective Evolutionary Algorithms. IEEE Transactions on Evolutionary Computation (2022 (Early Access)).
[15]
Simon Huband, Philip Hingston, Luigi Barone, and Lyndon While. 2006. A review of multiobjective test problems and a scalable test problem toolkit. IEEE Transactions on Evolutionary Computation 10, 5 (Oct. 2006), 477--506.
[16]
Hisao Ishibuchi, Ken Doi, and Yusuke Nojima. 2017. On the effect of normalization in MOEA/D for multi-objective and many-objective optimization. Complex & Intelligent Systems 3, 4 (Dec. 2017), 279--294.
[17]
H. Ishibuchi, L. He, and K. Shang. 2019. Regular Pareto Front Shape is not Realistic. In Proceedings of the IEEE Congress on Evolutionary Computation. Wellington, New Zealand, 2034--2041.
[18]
Hisao Ishibuchi, Ryo Imada, Yu Setoguchi, and Yusuke Nojima. 2018. How to Specify a Reference Point in Hypervolume Calculation for Fair Performance Comparison. Evolutionary Computation 26, 3 (Sept. 2018), 411--440.
[19]
Ke Li, Kalyanmoy Deb, Qingfu Zhang, and Sam Kwong. 2014. An evolutionary many-objective optimization algorithm based on dominance and decomposition. IEEE Transactions on Evolutionary Computation 19, 5 (Oct. 2014), 694--716.
[20]
Yiping Liu, Hisao Ishibuchi, Naoki Masuyama, and Yusuke Nojima. 2020. Adapting Reference Vectors and Scalarizing Functions by Growing Neural Gas to Handle Irregular Pareto Fronts. IEEE Transactions on Evolutionary Computation 24, 3 (June 2020), 439--453.
[21]
Yiping Liu, Hisao Ishibuchi, Gary G. Yen, Yusuke Nojima, Naoki Masuyama, and Yuyan Han. 2020. On the normalization in evolutionary multi-modal multiobjective optimization. In Proceedings of the IEEE Congress on Evolutionary Computation. Glasgow, United Kingdom, 1--8.
[22]
Dhish Kumar Saxena and Sarang Kapoor. 2019. On Timing the Nadir-Point Estimation and/or Termination of Reference-Based Multi- and Many-objective Evolutionary Algorithms. In Proceedings of Evolutionary Multi-Criterion Optimization, Vol. 11411. East Lansing, MI, USA, 191--202.
[23]
Ke Shang and Hisao Ishibuchi. 2020. A New Hypervolume-based Evolutionary Algorithm for Many-objective Optimization. IEEE Transactions on Evolutionary Computation 24, 5 (Oct. 2020), 839--852.
[24]
Ryoji Tanabe and Hisao Ishibuchi. 2020. An easy-to-use real-world multiobjective optimization problem suite. Applied Soft Computing 89 (April 2020).
[25]
Ye Tian, Ran Cheng, Xingyi Zhang, and Yaochu Jin. 2017. PlatEMO: A MATLAB platform for evolutionary multi-objective optimization. IEEE Computational Intelligence Magazine 12, 4 (Nov. 2017), 73--87.
[26]
Ye Tian, Xingyi Zhang, Chao Wang, and Yaochu Jin. 2020. An evolutionary algorithm for large-scale sparse multiobjective optimization problems. IEEE Transactions on Evolutionary Computation 24, 2 (2020), 380--393.
[27]
Bing Wang, Hemant Kumar Singh, and Tapabrata Ray. 2021. Adjusting normalization bounds to improve hypervolume based search for expensive multi-objective optimization. Complex & Intelligent Systems (Dec. 2021), 1--17.
[28]
Jiawei Yuan, Hai-Lin Liu, Fangqing Gu, Qingfu Zhang, and Zhaoshui He. 2021. Investigating the properties of indicators and an evolutionary many-objective algorithm using promising regions. IEEE Transactions on Evolutionary Computation 25, 1 (2021), 75--86.
[29]
Qingfu Zhang and Hui Li. 2007. MOEA/D: A multiobjective evolutionary algorithm based on decomposition. IEEE Transactions on Evolutionary Computation 11, 6 (Dec. 2007), 712--731.
Index Terms
- Effects of Objective Space Normalization in Multi-Objective Evolutionary Algorithms on Real-World Problems
Index terms have been assigned to the content through auto-classification.
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 ...
Towards estimating nadir objective vector using evolutionary approaches
GECCO '06: Proceedings of the 8th annual conference on Genetic and evolutionary computationNadir point plays an important role in multi-objective optimization because of its importance in estimating the range of objective values corresponding to desired Pareto-optimal solutions and also in using many classical interactive optimization ...
Evolutionary many-objective optimization using preference on hyperplane
GECCO Comp '14: Proceedings of the Companion Publication of the 2014 Annual Conference on Genetic and Evolutionary ComputationThis paper proposes to represent the preference of a decision maker by Gaussian functions on a hyperplane. The preference is used to evaluate non-dominated solutions as a second criterion instead of the crowding distance in NSGA-II. High performance of ...
Comments
Information & Contributors
Information
Published In
July 2023
1667 pages
Copyright © 2023 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: 12 July 2023
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Natural Science Foundation of China
- Guangdong Provincial Key Laboratory
- the Program for Guangdong Introducing Innovative and Enterpreneurial Teams
- The Stable Support Plan Program of Shenzhen Natural Science Fund
- Shenzhen Science and Technology Program
Conference
GECCO '23
Sponsor:
Acceptance Rates
Overall Acceptance Rate 1,669 of 4,410 submissions, 38%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 236Total Downloads
- Downloads (Last 12 months)211
- Downloads (Last 6 weeks)26
Reflects downloads up to 18 Aug 2024
Other Metrics
Citations
Cited By
View allView Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in