A Knee Point-Driven Evolutionary Algorithm for Many-Objective Optimization

By Xing-yi Zhang, Ye Tian, Yaochu Jin. 2015

766 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yaochu Jin
2. Xing-yi Zhang
3. Ye Tian
4. Ran Cheng
5. Yanan Sun
6. Gary G. Yen
7. Handing Wang
8. Mengjie Zhang

In Computational Theory and Mathematics

1. Yaochu Jin
2. Xing-yi Zhang
3. Ye Tian
4. Ran Cheng
5. Handing Wang
6. Yanan Sun
7. Gary G. Yen
8. Mengjie Zhang

In Management Science and Operations Research

1. Yaochu Jin
2. Ye Tian
3. Xing-yi Zhang
4. Ran Cheng
5. Gary G. Yen
6. Yanan Sun
7. Hangyu Zhu
8. Markus Olhofer

Citations in the corpus

• Real-Time Federated Evolutionary Neural Architecture Search (2020, neutral): “In practice, the Pareto solutions with the high test accuracies or those near the knee points [50]–[52] are preferred unless there are other strong user-specified preferences.”
• Localized Weighted Sum Method for Many-Objective Optimization (2018, background): “point-driven evolutionary algorithm [23], the improved twoarchive algorithm (Two_Arch2) [24] and [25]–[28].”
• A Strengthened Dominance Relation Considering Convergence and Diversity for Evolutionary Many-Objective Optimization (2018, methodology): “The proposed SDR is then embedded in NSGA-II [2], SPEA2 [20], PESA-II [21], GrEA [9], KnEA [14], and”
• A New Two-Stage Evolutionary Algorithm for Many-Objective Optimization (2019, methodology): “For instance, the -dominance method [17] employed a relaxed factor to compare the dominance relation between solutions; the preference order approach [18] used a ranking procedure to lower the adverse impact of the Pareto-dominance-based comparison; the fuzzy dominance method [19] was proposed with ”
• PlatEMO: A MATLAB Platform for Evolutionary Multi-Objective Optimization [Educational Forum] (2017, methodology): “For instance, there is a parameter rate denoting the ratio of selected knee points in K EA [45], and there are four parameters proC, disC, proM and disM in EAreal [91], [92], which denote the crossover probability, the distribution index of simulated binary cr ossover, the number of bits undergone m”
• A Method for a Posteriori Identification of Knee Points Based on Solution Density (2018, background): “Moreover, knee points are sometimes located in the middle of the Pareto front, contribute to a large dominated hypervolume [21].”
• A Classification-Based Surrogate-Assisted Evolutionary Algorithm for Expensive Many-Objective Optimization (2019, methodology): “, the evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach (NSGA-III) [11], the hypervolume (HV)based evolutionary algorithm [16], the knee-point driven evolutionary algorithm [17], the improved two-archive algorithm for many-objective optimiza”
• A benchmark test suite for evolutionary many-objective optimization (2017, unknown): “In recent years, a number of newalgorithmshave been proposed for dealingwithMaOPs [1], including the convergence enhancement based algorithms such as the grid-dominancebased evolutionary algorithm (GrEA) [2], the knee pointdriven evolutionary algorithm (KnEA) [3], the two-archive algorithm (Two_Arch”
• A Reference Vector Guided Evolutionary Algorithm for Many-Objective Optimization (2016, methodology): “In this section, empirical experiments are conducted on 15 benchmark test problems taken from two widely used test suites, i.e., the DTLZ [74] test suite (including the scaled version [39]) and the WFG test suite [71], to compare RVEA with five state-of-the-art MOEAs for many-objective optimization,”
• IGD Indicator-Based Evolutionary Algorithm for Many-Objective Optimization Problems (2018, methodology): “Particularly, NSGA-III [10], MOEA/D [14], HypE [34], RVEA [13], and KnEA [30] are selected as the state-of-the-art peer competitors.”
• Benchmark Problems and Performance Indicators for Search of Knee Points in Multiobjective Optimization (2020, methodology): “There are also methods which do not belong to the above three categories, such as the objective reduction [24], the shift-based density estimation [25], the two-archive strategy [26], the boundary elimination selection [27] and the knee-point driven MOEAs [28].”
• Multi-Objective Evolutionary Federated Learning (2018, methodology): “, the evolutionary many-objective optimization algorithm using referencepoint based non-dominated sorting approach [23], the kneedriven evolutionary algorithm for many-objective optimization [24], and the reference vector guided evolutionary for manyobjective optimization [25].”
• A Decision Variable Clustering-Based Evolutionary Algorithm for Large-Scale Many-Objective Optimization (2018, methodology): “Table VII presents the statistical results of the IGD values obtained by the five algorithms on LSMOP1–LSMOP9 with five objectives and 500 decision variables via 20 independent runs, where the parameter T for controlling the ratio of knee points in KnEA is set to 0.5, and all the other parameters ar”
• An Indicator-Based Multiobjective Evolutionary Algorithm With Reference Point Adaptation for Better Versatility (2018, background): “such as the grid dominance-based evolutionary algorithm [7] and knee point driven evolutionary algorithm [8], among many others [2].”