Surrogate-assisted evolutionary algorithms are widely used to solve expensive optimization problems due to their high search efficiency. However, a single model struggles to fit various fitness landscapes with different characteristics. How to adaptively select the most suitable model based on the problem’s fitness landscape characteristics remains an open research area. Therefore, this paper proposes an adaptive surrogate model selection framework based on an SISSO model selector. This method extracts problem features from the optimization process and dynamically selects the surrogate model most suitable for the current stage via the SISSO model selector, thereby enhancing the algorithm’s adaptability to different function characteristics. Experiments on CEC2022 test functions show that the proposed method achieves significantly lower mean errors and stable variances on most functions. Particularly on functions F10 and F11, the SISSO method reduces the mean error by more than an order of magnitude compared to methods like ElasticNet, Lars, Lasso, and Ridge, demonstrating excellent comprehensive performance.
References
[1]
Shao, W.W, Zhu, Y.G. and Hu, C. (2024) Application of Improved RRT Algorithm in Path Planning. Journal of Nanyang Normal University, 23, 58-63.
[2]
Yang, Y., Liu, J. and Tan, S. (2021) A Multi-Objective Evolutionary Algorithm for Steady-State Constrained Multi-Objective Optimization Problems. Applied Soft Computing, 101, Article ID: 107042. https://doi.org/10.1016/j.asoc.2020.107042
[3]
Qiu, X., Xu, J., Xu, Y. and Tan, K.C. (2018) A New Differential Evolution Algorithm for Minimax Optimization in Robust Design. IEEE Transactions on Cybernetics, 48, 1355-1368. https://doi.org/10.1109/tcyb.2017.2692963
[4]
Wei, J. and Niu, H. (2022) Offline Data-Driven Particle Swarm Optimization Assisted by Selective Surrogate Ensembles and Hybrid Search Strategies. 2022 34th Chinese Control and Decision Conference (CCDC), Hefei, 15-17 August 2022, 4010-4016. https://doi.org/10.1109/ccdc55256.2022.10033635
[5]
Su, G., Sun, W. and Zhao, Y. (2023) Machine Learning Classifier-Based Dynamic Surrogate Model for Structural Reliability Analysis. Structure and Infrastructure Engineering, 21, 525-537. https://doi.org/10.1080/15732479.2023.2218847
[6]
Luo, S. (2023) Synthetic Minority Oversampling Technique Based on Adaptive Noise Optimization and Fast Search for Local Sets for Random Forest. International Journal of Pattern Recognition and Artificial Intelligence, 37, Article ID: 2259038. https://doi.org/10.1142/s0218001422590388
[7]
Li, M., Sadoughi, M., Hu, Z. and Hu, C. (2020) A Hybrid Gaussian Process Model for System Reliability Analysis. Reliability Engineering & System Safety, 197, Article ID: 106816. https://doi.org/10.1016/j.ress.2020.106816
[8]
He, C., Zhang, Y., Gong, D. and Ji, X. (2023) A Review of Surrogate-Assisted Evolutionary Algorithms for Expensive Optimization Problems. Expert Systems with Applications, 217, Article ID: 119495. https://doi.org/10.1016/j.eswa.2022.119495
[9]
Zuo, S.Y. (2024) Parameter Analysis Modeling and Application Based on Additive Gaussian Process. Master’s Thesis, Dalian University of Technology.
[10]
Zhang, M. (2025) Electric Vehicle Charging Load Prediction Based on Optimized Random Forest Algorithm. Digital Communication World, No. 6, 26-28.
[11]
Liang, X. (2024) Prediction of Landslide Displacement Data Based on Support Vector Regression. Master’s Thesis, Lanzhou University of Technology.
[12]
Xiao, T.C. (2022) Optimal Latin Hypercube Design under Symmetric Variable Conditions. Master’s Thesis, Central University of Finance and Economics.
[13]
Gong, L.L. (2022) Research on Software Defect Prediction Method Combined with Multiple Features. Master’s Thesis, Hangzhou University of Electronic Science and Technology.
[14]
Cui, J.S., Liu, X.C.,Yang, M.H., et al. (2017) Automatic Selection Framework and Empirical Analysis of Optimization Algorithm Based on Meta-Learning Recommendation. Computer Applications, 37, 1105-1110.
[15]
Li, B., Wang, D., Yu, M., He, C., Li, X., Zhai, J., et al. (2025) Accelerating Multi-Objective Catalytic Material Design: A Model-Based Method. Chinese Chemical Letters, 36, Article ID: 110454. https://doi.org/10.1016/j.cclet.2024.110454
[16]
Li, B., Chen, J., Shi, X., Zhang, Y., Lv, D., Liu, L., et al. (2016) On the Convergence of Multivariant Optimization Algorithm. Applied Soft Computing, 48, 230-239. https://doi.org/10.1016/j.asoc.2016.07.001
