Active Learning in Genetic Programming: Guiding Efficient Data Collection for Symbolic Regression

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@Article{Haut:ieeeTEC,

• author = "Nathan Haut and Wolfgang Banzhaf and Bill Punch",
• title = "Active Learning in Genetic Programming: Guiding Efficient Data Collection for Symbolic Regression",
• journal = "IEEE Transactions on Evolutionary Computation",
• note = "Early Access",
• keywords = "genetic algorithms, genetic programming, Training, Data models, Uncertainty, Mathematical models, Measurement, Machine learning, Labeling, Genetic programming, Training data, Computational modeling, Active learning, symbolic regression",
• ISSN = "1089-778X",
• DOI = "doi:10.1109/TEVC.2024.3471341",
• size = "13 pages",
• abstract = "This paper examines various methods of computing uncertainty and diversity for active learning in genetic programming. We found that the model population in genetic programming can be exploited to select informative training data points by using a model ensemble combined with an uncertainty metric. We explored several uncertainty metrics and found that differential entropy performed the best. We also compared two data diversity metrics and found that correlation as a diversity metric performs better than minimum Euclidean distance, although there are some drawbacks that prevent correlation from being used on all problems. Finally, we combined uncertainty and diversity using a Pareto optimization approach to allow both to be considered in a balanced way to guide the selection of informative and unique data points for training.",
• notes = "also known as \cite{10700803} See also \cite{DBLP:journals/corr/abs-2308-00672}",

}

Genetic Programming entries for Nathaniel Haut Wolfgang Banzhaf William F Punch

Citations