logicGP - A Framework for Literal Based Classification with a Focus on Software Architecture and Open Source Implementation

Created by W.Langdon from gp-bibliography.bib Revision:1.8528

@InProceedings{nunkesser:2025:GECCOcomp,

• author = "Robin Nunkesser",
• title = "{logicGP} - A Framework for Literal Based Classification with a Focus on Software Architecture and Open Source Implementation",
• booktitle = "Open Source Software for Evolutionary Computation",
• year = "2025",
• editor = "Stefan Wagner and Michael Affenzeller",
• pages = "2063--2071",
• address = "Malaga, Spain",
• series = "GECCO '25 Companion",
• month = "14-18 " # jul,
• organisation = "SIGEVO",
• publisher = "Association for Computing Machinery",
• publisher_address = "New York, NY, USA",
• keywords = "genetic algorithms, genetic programming, classification, interpretable machine learning, open source, SNP, bioinformatics, ML.NET",
• isbn13 = "979-8-4007-1464-1",
• URL = "https://doi.org/10.1145/3712255.3734300",
• DOI = "doi:10.1145/3712255.3734300",
• size = "9 pages",
• abstract = "This paper presents a Genetic Programming based framework called logicGP for classification with literal based models and the open source software created and used for the implementation. The used prediction model is a linear combination of logical monomials. The underlying algorithm is designed to be interpretable and to allow for a high degree of predictive ability. The implementation of the algorithm is done in C# with open source code and is designed for high compatibility with Microsoft's ML.NET. The algorithm is presented as an extensible framework and different parameterizations for different tasks are discussed. Additionally, the paper presents the open source code created for the framework and discusses the software architecture used. The algorithm is tested on simulated data for binary classification with three categories (inspired by the analysis of SNP data) and on selected real data for multiclass classification. The experiments show that the algorithm is able to achieve a high degree of predictive ability while maintaining a high degree of interpretability.",
• notes = "GECCO-2025 EvoOSS workshop A Recombination of the 34th International Conference on Genetic Algorithms (ICGA) and the 30th Annual Genetic Programming Conference (GP)",

}

Genetic Programming entries for Robin Nunkesser

Citations