go back

Automatic Algorithm Selection for Evolutionary Multi-Objective Optimization

Ye Tian, Shichen Peng, Tobias Rodemann, Xingyi Zhang, Yaochu Jin, "Automatic Algorithm Selection for Evolutionary Multi-Objective Optimization", 2019 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 3225-3232, 2020.


In the last two decades, many evolutionary algorithms have shown promising performance in solving a variety of multi-objective optimization problems (MOPs). Since there does not exist an evolutionary algorithm having the best performance on all the MOPs, it is unreasonable to use a single evolutionary algorithm to tackle all the MOPs. While many real-world MOPs are computationally expensive, selecting the best evolutionary algorithm from multiple candidates via empirical comparisons is also impractical. To address this issue, this paper proposes an automatic algorithm selection method for picking the most suitable evolutionary algorithm for a given MOP. The proposed method establishes a predictor based on the performance of a set of candidate evolutionary algorithms on multiple benchmark MOPs, where the inputs of the predictor are the explicit and implicit features of an MOP, and the output is the index of the evolutionary algorithm having the best performance on the MOP. Experimental results indicate that the evolutionary algorithm suggested by the proposed method ranks high among all the candidate evolutionary algorithms. As a result, the proposed method is useful for engineers to select an evolutionary algorithm for their applications.

Download Bibtex file Download PDF