Genetic Programming for Instance Transfer Learning in Symbolic Regression

Created by W.Langdon from gp-bibliography.bib Revision:1.7970

@Article{Chen:2020:CYB,

• author = "Qi Chen and Bing Xue and Mengjie Zhang",
• journal = "IEEE Transactions on Cybernetics",
• title = "Genetic Programming for Instance Transfer Learning in Symbolic Regression",
• year = "2022",
• volume = "52",
• number = "1",
• pages = "25--38",
• month = jan,
• keywords = "genetic algorithms, genetic programming, Task analysis, Estimation, Multitasking, Machine learning, Data models, Cybernetics, instance weighting, transfer learning",
• ISSN = "2168-2275",
• DOI = "doi:10.1109/TCYB.2020.2969689",
• abstract = "Transfer learning has attracted more attention in the machine-learning community recently. It aims to improve the learning performance on the domain of interest with the help of the knowledge acquired from a similar domain(s). However, there is only a limited number of research on tackling transfer learning in genetic programming for symbolic regression. This article attempts to fill this gap by proposing a new instance weighting framework for transfer learning in genetic programming-based symbolic regression. In the new framework, differential evolution is employed to search for optimal weights for source-domain instances, which helps genetic programming to identify more useful source-domain instances and learn from them. Meanwhile, a density estimation method is used to provide good starting points to help the search for the optimal weights while discarding some irrelevant or less important source-domain instances before learning regression models. The experimental results show that compared with genetic programming and support vector regression that learn only from the target instances, and learning from a mixture of instances from the source and target domains without any transfer learning component, the proposed method can evolve regression models which not only achieve notably better cross-domain generalization performance in stability but also reduce the trend of overfitting effectively. Meanwhile, these models are generally much simpler than those generated by the other GP methods.",
• notes = "Also known as \cite{9007621}",

}

Genetic Programming entries for Qi Chen Bing Xue Mengjie Zhang

Citations