中文

Improving Evaluation of Recombination-based Cartesian Genetic Programming

神经与进化计算 2026-05-28 v1 人工智能 符号计算

摘要

Cartesian Genetic Programming has traditionally been using mutation as its main and often sole genetic operator to drive evolutionary search. Despite advancements in recent years, recombinationbased approaches have long been avoided, due to apparent lack of performance gains. This study examines two recently suggested recombination-based operators, subgraph crossover and discrete phenotypic recombination on SRBench, a benchmarking platform for symbolic regression. Using the implementations provided in the TinyverseGP framework, we perform hyperparameter optimisation of the respective representations with these two operators. Our work demonstrates that hyperparameter optimisation can lead to improvements in performance for recombination-based Cartesian Genetic Programming.

关键词

引用

@article{arxiv.2605.28353,
  title  = {Improving Evaluation of Recombination-based Cartesian Genetic Programming},
  author = {Duy Long Tran and Anja Jankovic and Marie Anastacio and Holger Hoos and Roman Kalkreuth},
  journal= {arXiv preprint arXiv:2605.28353},
  year   = {2026}
}

备注

Accepted for presentation as workshop paper in the graph-based genetic programming workshop (GGP) at the Genetic and Evolutionary Computation Conference (GECCO). To appear in the GECCO'26 conference companion. GECCO'26 will be held July 13-17, 2026 in San Jose, Costa Rica