- author = "Hengzhe Zhang and Qi Chen and Bing Xue and Wolfgang Banzhaf and Mengjie Zhang",
- title = "A Double Lexicase Selection Operator for Bloat Control in Evolutionary Feature Construction for Regression",
- booktitle = "Proceedings of the 2023 Genetic and Evolutionary Computation Conference",
- year = "2023",
- editor = "Sara Silva and Luis Paquete and Leonardo Vanneschi and Nuno Lourenco and Ales Zamuda and Ahmed Kheiri and Arnaud Liefooghe and Bing Xue and Ying Bi and Nelishia Pillay and Irene Moser and Arthur Guijt and Jessica Catarino and Pablo Garcia-Sanchez and Leonardo Trujillo and Carla Silva and Nadarajen Veerapen",
- pages = "1194--1202",
- address = "Lisbon, Portugal",
- series = "GECCO '23",
- month = "15-19 " # jul,
- organisation = "SIGEVO",
- publisher = "Association for Computing Machinery",
- publisher_address = "New York, NY, USA",
- keywords = "genetic algorithms, genetic programming, bloat control, evolutionary feature construction",
- isbn13 = "9798400701191",
-
URL = "
https://doi.org/10.1145/3583131.3590365",
-
DOI = "
10.1145/3583131.3590365",
-
suppl_url = "
https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3583131.3590365&file=p1194-zhang-suppl.pdf",
- size = "9 pages",
- abstract = "Evolutionary feature construction is an important technique in the machine learning domain for enhancing learning performance. However, traditional genetic programming-based feature construction methods often suffer from bloat, which means the sizes of constructed features increase excessively without improved performance. To address this issue, this paper proposes a double-stage lexicase selection operator to control bloat while not damaging search effectiveness. This new operator contains a two-stage selection process, where the first stage selects individuals based on fitness values and the second stage selects individuals based on tree sizes. Therefore, the proposed operator can control bloat meanwhile leveraging the advantage of the lexicase selection operator. Experimental results on 98 regression datasets show that compared to the traditional bloat control method of having a depth limit, the proposed selection operator not only significantly reduces the sizes of constructed features on all datasets but also keeps a similar level of predictive performance. A comparative experiment with seven bloat control methods shows that the double lexicase selection operator achieves the best trade-off between the model performance and the model size.",
-
notes = "
GECCO-2023 A Recombination of the 32nd International Conference on Genetic Algorithms (ICGA) and the 28th Annual Genetic Programming Conference (GP)",
