Skip to main content
Log in

Investigating the influence of survival selection and fitness estimation method in genotype-based surrogate-assisted genetic programming

Artificial Life and Robotics Aims and scope Submit manuscript

Abstract

This paper focuses on surrogate-assisted genetic programming (SAGP), an efficient evolutionary program optimization approach based on the surrogate estimation of the fitness value. In particular, we use a genotype-based SAGP (G-SAGP), which uses the nearest neighbor method according to the tree structure similarity as the surrogate evaluation. This article investigates the influence of the survival selection and the fitness estimation method in G-SAGP to improve its performance. For the survival selection, we compare the (\(\mu ,\lambda\)) selection and the (\(\mu +\lambda\)) selection, which are both commonly used in evolutionary computation methods. On the other hand, the conventional G-SAGP uses the nearest neighbor method for the fitness estimation method, while this article attempts the k-nearest weighted average regression. We conduct experiments using symbolic regression problems, which are usually used as the GP benchmark. The experiments compare different survival selection methods and different fitness estimation methods. The experimental results show that G-SAGP using the (\(\mu +\lambda\)) selection can reduce the number of generations while maintaining a higher success ratio. In addition, for the fitness estimation method, the nearest neighbor regression is enough to achieve a high success ratio with a smaller number of generations. In contrast, the k-nearest weighted average regression with a large k can perform better in some benchmark problems.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Notes

  1. Protected division. Division that returns 1 if the denominator is 0.

  2. Positive / negative inversion.

References

  1. Ben WC, Nehdi ML (2021) Genetic programming based symbolic regression for shear capacity prediction of SFRC beams. Constr Build Mater 280(122):523. https://doi.org/10.1016/j.conbuildmat.2021.122523

    Article  Google Scholar 

  2. Bi Y, Xue B, Zhang M (2022) Using a small number of training instances in genetic programming for face image classification. Inf Sci 593:488–504. https://doi.org/10.1016/j.ins.2022.01.055

    Article  Google Scholar 

  3. Espejo PG, Ventura S, Herrera F (2010) A survey on the application of genetic programming to classification. IEEE Trans Syst Man Cyber Part C 40(2):121–144. https://doi.org/10.1109/TSMCC.2009.2033566

    Article  Google Scholar 

  4. Goldberg DE (1989) Genetic algorithm in search. Optimization and machine learning. Addision-Wesley, Boston

    MATH  Google Scholar 

  5. Hildebrandt T, Branke J (2015) On using surrogates with genetic programming. Evolut Comput 23(3):343–367. https://doi.org/10.1162/EVCO_a_00133

    Article  Google Scholar 

  6. Jin Y (2011) Surrogate-assisted evolutionary computation: recent advances and future challenges. Swarm Evolut Comput 1(2):61–70. https://doi.org/10.1016/j.swevo.2011.05.001

    Article  Google Scholar 

  7. Kino S, Harada T, Thawonmas R (2020) Proposal of surrogate model for genetic programming based on program structure similarity. Annual Conf Soc Instrum Control Eng Jpn (SICE). https://doi.org/10.23919/SICE48898.2020.9240324

    Article  Google Scholar 

  8. Koza J (1992) Genetic programming on the programming of computers by means of natural selection. MIT Press, London

    MATH  Google Scholar 

  9. McDermott J, White DR, Luke S, Manzoni L, Castelli M, Vanneschi L, Jaskowski W, Krawiec K, Harper R, De Jong K, O’Reilly UM (2012) Genetic programming needs better benchmarks. Proce Annu Conf Genetic Evolut Comput. https://doi.org/10.1145/2330163.2330273

    Article  Google Scholar 

  10. Moraglio A, Poli R (2005) Geometric landscape of homologous crossover for syntactic trees. IEEE Congr Evolut Comput 1:427–434. https://doi.org/10.1109/CEC.2005.1554715

    Article  Google Scholar 

  11. Nguyen S, Zhang M, Johnston M, Tan KC (2013) A computational study of representations in genetic programming to evolve dispatching rules for the job shop scheduling problem. IEEE Trans Evolut Comput 17(5):621–639. https://doi.org/10.1109/TEVC.2012.2227326

    Article  Google Scholar 

  12. Nguyen S, Zhang M, Tan KC (2017) Surrogate-assisted genetic programming with simplified models for automated design of dispatching rules. IEEE Trans Cybern 47(9):2951–2965. https://doi.org/10.1109/TCYB.2016.2562674

    Article  Google Scholar 

  13. Pinedo ML (2012) Scheduling: theory, algorithms, and systems. Springer-Verlag, New York

    Book  MATH  Google Scholar 

  14. Poli R, Langdon WB, McPhee NF (2008) A field guide to genetic programming. With contributions by J. R. Koza. http://www.gp-field-guide.org.uk

  15. Tong H, Huang C, Minku LL, Yao X (2021) Surrogate models in evolutionary single-objective optimization: a new taxonomy and experimental study. Inf Sci 562:414–437. https://doi.org/10.1016/j.ins.2021.03.002

    Article  Google Scholar 

  16. Yang R, Kalnis P, Tung AKH (2005) Similarity evaluation on tree-structured data. Proc ACM SIGMOD Int Conf Manag Data. https://doi.org/10.1145/1066157.1066243

    Article  Google Scholar 

Download references

Acknowledgements

This research was partially supported by a Japan Society for the Promotion of Science Grant-in-Aid for Young Scientists, Grant Number JP21K17826.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Tomohiro Harada.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This work was presented in part at the joint symposium of the 27th International Symposium on Artificial Life and Robotics, the 7th International Symposium on BioComplexity, and the 5th International Symposium on Swarm Behavior and Bio-Inspired Robotics (Online, January 25– 27, 2022).

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Harada, T., Kino, S. & Thawonmas, R. Investigating the influence of survival selection and fitness estimation method in genotype-based surrogate-assisted genetic programming. Artif Life Robotics 28, 181–191 (2023). https://doi.org/10.1007/s10015-022-00821-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10015-022-00821-3

Keywords

Navigation