Automated Grammar-based Feature Selection in Symbolic Regression

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

@InProceedings{ali:2022:GECCO,

• author = "Muhammad Sarmad Ali and Meghana Kshirsagar and Enrique Naredo and Conor Ryan",
• title = "Automated Grammar-based Feature Selection in Symbolic Regression",
• booktitle = "Proceedings of the 2022 Genetic and Evolutionary Computation Conference",
• year = "2022",
• editor = "Alma Rahat and Jonathan Fieldsend and Markus Wagner and Sara Tari and Nelishia Pillay and Irene Moser and Aldeida Aleti and Ales Zamuda and Ahmed Kheiri and Erik Hemberg and Christopher Cleghorn and Chao-li Sun and Georgios Yannakakis and Nicolas Bredeche and Gabriela Ochoa and Bilel Derbel and Gisele L. Pappa and Sebastian Risi and Laetitia Jourdan and Hiroyuki Sato and Petr Posik and Ofer Shir and Renato Tinos and John Woodward and Malcolm Heywood and Elizabeth Wanner and Leonardo Trujillo and Domagoj Jakobovic and Risto Miikkulainen and Bing Xue and Aneta Neumann and Richard Allmendinger and Inmaculada Medina-Bulo and Slim Bechikh and Andrew M. Sutton and Pietro Simone Oliveto",
• pages = "902--910",
• address = "Boston, USA",
• series = "GECCO '22",
• month = "9-13 " # jul,
• organisation = "SIGEVO",
• publisher = "Association for Computing Machinery",
• publisher_address = "New York, NY, USA",
• keywords = "genetic algorithms, genetic programming, feature selection, symbolic regression, production ranking, grammatical evolution, grammar pruning",
• isbn13 = "978-1-4503-9237-2",
• DOI = "doi:10.1145/3512290.3528852",
• abstract = "With the growing popularity of machine learning (ML), regression problems in many domains are becoming increasingly high-dimensional. Identifying relevant features from a high-dimensional dataset still remains a significant challenge for building highly accurate machine learning models.Evolutionary feature selection has been used for high-dimensional symbolic regression using Genetic Programming (GP). While grammar based GP, especially Grammatical Evolution (GE), has been extensively used for symbolic regression, no systematic grammar-based feature selection approach exists. This work presents a grammar-based feature selection method, Production Ranking based Feature Selection (PRFS), and reports on the results of its application in symbolic regression.The main contribution of our work is to demonstrate that the proposed method can not only consistently select the most relevant features, but also significantly improves the generalization performance of GE when compared with several state-of-the-art ML-based feature selection methods. Experimental results on benchmark symbolic regression problems show that the generalization performance of GE using PRFS was significantly better than that of a state-of-the-art Random Forest based feature selection in three out of four problems, while in fourth problem the performance was the same.",
• notes = "GECCO-2022 A Recombination of the 31st International Conference on Genetic Algorithms (ICGA) and the 27th Annual Genetic Programming Conference (GP)",

}

Genetic Programming entries for Muhammad Sarmad Ali Meghana Kshirsagar Enrique Naredo Conor Ryan

Citations