TY - JOUR
T1 - MOTEA-II: A Collaborative Multi-Objective Transformation Based Evolutionary Algorithm for Bi-Level Optimization
AU - Chen, Lei
AU - Cheung, Yiu-ming
AU - Liu, Hai-Lin
AU - Lai, Yutao
N1 - Funding Information:
This work was supported in part by the NSFC / Research Grants Council (RGC) Joint Research Scheme under the grant: N HKBU214/21, the General Research Fund of RGC under the grants: 12202622 and 12201323, the RGC Senior Research Fellow Scheme with the grant: SRFS2324-2S02, the Hong Kong Baptist University under the grant RC-FNRA-IG/23-24/SCI/02, National Natural Science Foundation of China 62172110, Natural Science Foundation of Guangdong Province 2024A1515010196, and supported by Hong Kong Scholars Program 2022.
PY - 2025/2/4
Y1 - 2025/2/4
N2 - Evolutionary algorithms (EAs) for optimization have received wide attention due to their robustness and practicality. However, the traditional way of asynchronously handling bi-level optimization problems (BLOPs) ignores the benefits brought by effective upper-and lower-level collaboration. To address this issue, this paper proposes a collaborative multi-objective transformation (MOT)-based evolutionary algorithm (MOTEA-II). In MOTEA-II, the BLOP is handled within a decomposition-based multi-objective optimization paradigm using a two-stage collaborative MOT strategy. The stage-1 MOT focuses on multiple lower-level optimizations and collaboration, while stage-2 collaborates the upper-level optimization with lower-level optimization, which makes simultaneously horizontal and vertical optimization information sharing in bi-level optimization possible. In addition, a dynamic decomposition strategy is further proposed to reconstruct the hierarchy relationship in collaborative multi-objective optimization, facilitating the adaptive and flexible importance control of the upper-level objective optimization and lower-level optimality satisfaction for better bi-level search efficiency. Empirical studies are conducted on two groups of commonly used BLOP benchmark suites and four practical applications. Experimental results show that the proposed collaborative MOTEA-II can achieve performance comparable to that of the previous MOTEA and three other representative EA-based bi-level optimization approaches, but using much fewer computational resources.
AB - Evolutionary algorithms (EAs) for optimization have received wide attention due to their robustness and practicality. However, the traditional way of asynchronously handling bi-level optimization problems (BLOPs) ignores the benefits brought by effective upper-and lower-level collaboration. To address this issue, this paper proposes a collaborative multi-objective transformation (MOT)-based evolutionary algorithm (MOTEA-II). In MOTEA-II, the BLOP is handled within a decomposition-based multi-objective optimization paradigm using a two-stage collaborative MOT strategy. The stage-1 MOT focuses on multiple lower-level optimizations and collaboration, while stage-2 collaborates the upper-level optimization with lower-level optimization, which makes simultaneously horizontal and vertical optimization information sharing in bi-level optimization possible. In addition, a dynamic decomposition strategy is further proposed to reconstruct the hierarchy relationship in collaborative multi-objective optimization, facilitating the adaptive and flexible importance control of the upper-level objective optimization and lower-level optimality satisfaction for better bi-level search efficiency. Empirical studies are conducted on two groups of commonly used BLOP benchmark suites and four practical applications. Experimental results show that the proposed collaborative MOTEA-II can achieve performance comparable to that of the previous MOTEA and three other representative EA-based bi-level optimization approaches, but using much fewer computational resources.
KW - Collaborative multi-objective transformation
KW - evolutionary bi-level optimization
KW - dynamic decomposition
U2 - 10.1109/TEVC.2025.3538611
DO - 10.1109/TEVC.2025.3538611
M3 - Journal article
SN - 1941-0026
SP - 1
EP - 16
JO - IEEE Transactions on Evolutionary Computation
JF - IEEE Transactions on Evolutionary Computation
ER -