A twin-archive guided decomposition based multi/many-objective evolutionary algorithm

Decomposition-based Multi-Objective Evolutionary Algorithms (DMOEAs) gained popularity due to their ability to handle Multi/Many-objective Optimization Problems (MOPs/MaOPs). On the other hand, the weight vector adaptation strategy in DMOEAs is an essential ingredient for better performance, especially when dealing with MaOPs with irregular Pareto Front (PF). In general, an effective weight vector adaptation strategy faces challenges like identification of ineffective weight vectors, the proper timing and frequency of adaptation, reallocation of ineffective weight vectors and effective estimation of reference points. DMOEAs proposed in the literature try to address a subset of these issues, but fail to handle all of them simultaneously. In this paper, we propose a DMOEA namely 'A Twin-Archive Guided Decomposition based Multi/Many-objective Evolutionary Algorithm' (TAG-DMOEA) that basically employs two archives to update weight vectors and to estimate nadir point, separately. The better performance of TAG-DMOEA is validated over 10 representative state-of-the-art algorithms on 16 test problems with the number of objectives ranging from 2 to 10. The empirical results demonstrate the effectiveness of TAG-DMOEA on MOPs/MaOPs in both regular and irregular PFs.

Automated summary

Decomposition-based Multi-Objective Evolutionary Algorithms (DMOEAs) have gained popularity for their ability to handle Multi/Many-objective Optimization Problems (MOPs/MaOPs). However, the weight vector adaptation strategy in DMOEAs still faces challenges in effectively handling irregular Pareto Front (PF). Existing DMOEAs in the literature address only a subset of these challenges, failing to handle all of them simultaneously. This paper proposes a new DMOEA called TAG-DMOEA, which utilizes two archives for weight vector updating and nadir point estimation, showing better performance on MOPs/MaOPs with both regular and irregular PFs.