Weak Convergence Detection-based Dynamic Reference Point Specification in SMS-EMOA

In the evolutionary multi-objective optimization (EMO) field, the hypervolume (HV) indicator is one of the most popular performance indicators. It is not only used for performance evaluation of EMO algorithms (EMOAs) but also adopted in EMOAs for selection (e.g., SMS-EMOA). The specification of a reference point for HV calculation has a large effect on the performance of SMS-EMOA. Thus, the reference point specification should be carefully treated in SMS-EMOA. In this paper, the importance of the dynamic reference point specification in SMS-EMOA is explained first. Then a new dynamic reference point specification mechanism, which is based on weak convergence detection is introduced for SMS-EMOA. Experimental comparisons are conducted for different specification methods in SMS-EMOA: a linearly decreasing mechanism and two static mechanisms. Our results demonstrate the effectiveness of the proposed dynamic reference point specification mechanism.

[1]  Hisao Ishibuchi,et al.  Reference point specification in hypervolume calculation for fair comparison and efficient search , 2017, GECCO.

[2]  M. Hansen,et al.  Evaluating the quality of approximations to the non-dominated set , 1998 .

[3]  Heike Trautmann,et al.  Statistical Methods for Convergence Detection of Multi-Objective Evolutionary Algorithms , 2009, Evolutionary Computation.

[4]  Hisao Ishibuchi,et al.  Performance of Decomposition-Based Many-Objective Algorithms Strongly Depends on Pareto Front Shapes , 2017, IEEE Transactions on Evolutionary Computation.

[5]  Jesús García,et al.  Introducing a robust and efficient stopping criterion for MOEAs , 2010, IEEE Congress on Evolutionary Computation.

[6]  Carlos A. Coello Coello,et al.  A Study of the Parallelization of a Coevolutionary Multi-objective Evolutionary Algorithm , 2004, MICAI.

[7]  Marc Schoenauer,et al.  A Steady Performance Stopping Criterion for Pareto-based Evolutionary Algorithms , 2004 .

[8]  Hisao Ishibuchi,et al.  How to Specify a Reference Point in Hypervolume Calculation for Fair Performance Comparison , 2018, Evolutionary Computation.

[9]  Marco Laumanns,et al.  Performance assessment of multiobjective optimizers: an analysis and review , 2003, IEEE Trans. Evol. Comput..

[10]  Paul L. Meyer,et al.  Introductory Probability and Statistical Applications , 1970 .

[11]  Hisao Ishibuchi,et al.  Use of Two Reference Points in Hypervolume-Based Evolutionary Multiobjective Optimization Algorithms , 2018, PPSN.

[12]  Lothar Thiele,et al.  Multiobjective Optimization Using Evolutionary Algorithms - A Comparative Case Study , 1998, PPSN.

[13]  H. Ishibuchi,et al.  On the effect of normalization in MOEA/D for multi-objective and many-objective optimization , 2017 .

[14]  Qingfu Zhang,et al.  A Generator for Multiobjective Test Problems With Difficult-to-Approximate Pareto Front Boundaries , 2019, IEEE Transactions on Evolutionary Computation.

[15]  Qingfu Zhang,et al.  MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition , 2007, IEEE Transactions on Evolutionary Computation.

[16]  Hisao Ishibuchi,et al.  Dynamic Specification of a Reference Point for Hypervolume Calculation in SMS-EMOA , 2018, 2018 IEEE Congress on Evolutionary Computation (CEC).

[17]  Lothar Thiele,et al.  The Hypervolume Indicator Revisited: On the Design of Pareto-compliant Indicators Via Weighted Integration , 2007, EMO.

[18]  Marco Laumanns,et al.  Scalable multi-objective optimization test problems , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[19]  Hisao Ishibuchi,et al.  A new R2 indicator for better hypervolume approximation , 2018, GECCO.

[20]  Heike Trautmann,et al.  OCD: Online Convergence Detection for Evolutionary Multi-Objective Algorithms Based on Statistical Testing , 2009, EMO.

[21]  Eckart Zitzler,et al.  HypE: An Algorithm for Fast Hypervolume-Based Many-Objective Optimization , 2011, Evolutionary Computation.

[22]  Jie Zhang,et al.  A Simple and Fast Hypervolume Indicator-Based Multiobjective Evolutionary Algorithm , 2015, IEEE Transactions on Cybernetics.

[23]  Nicola Beume,et al.  SMS-EMOA: Multiobjective selection based on dominated hypervolume , 2007, Eur. J. Oper. Res..

[24]  Heike Trautmann,et al.  A Convergence Criterion for Multiobjective Evolutionary Algorithms Based on Systematic Statistical Testing , 2008, PPSN.

[25]  Elizabeth Montero,et al.  An Improved S-Metric Selection Evolutionary Multi-Objective Algorithm With Adaptive Resource Allocation , 2018, IEEE Access.

[26]  R. Lyndon While,et al.  A review of multiobjective test problems and a scalable test problem toolkit , 2006, IEEE Transactions on Evolutionary Computation.

[27]  Kalyanmoy Deb,et al.  Running performance metrics for evolutionary multi-objective optimizations , 2002 .

[28]  Hisao Ishibuchi,et al.  Hypervolume Subset Selection for Triangular and Inverted Triangular Pareto Fronts of Three-Objective Problems , 2017, FOGA '17.

[29]  Heike Trautmann,et al.  A Taxonomy of Online Stopping Criteria for Multi-Objective Evolutionary Algorithms , 2011, EMO.

[30]  Kalyanmoy Deb,et al.  An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point Based Nondominated Sorting Approach, Part II: Handling Constraints and Extending to an Adaptive Approach , 2014, IEEE Transactions on Evolutionary Computation.

[31]  Ye Tian,et al.  PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimization [Educational Forum] , 2017, IEEE Computational Intelligence Magazine.