Refining Neural Network with Symbolic Regression

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

@InProceedings{wei:2025:GECCOcomp,

• author = "Wei Wei2 and Qiang Lu and Can Huang and Jake Luo",
• title = "Refining Neural Network with Symbolic Regression",
• booktitle = "Proceedings of the 2025 Genetic and Evolutionary Computation Conference Companion",
• year = "2025",
• editor = "Roman Kalkreuth and Alexander Brownlee",
• pages = "923--926",
• 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, cartesian genetic programming, neural network refinement, symbolic regression, neural network compression, Real World Applications: Poster",
• isbn13 = "979-8-4007-1464-1",
• URL = "https://doi.org/10.1145/3712255.3726565",
• DOI = "doi:10.1145/3712255.3726565",
• size = "4 pages",
• abstract = "Classical neural network (NN) compression methods, such as NN pruning and distillation, focus on reducing the NN size. However, these methods often sacrifice accuracy in the process. To address this issue, we propose a novel NN refinement method based on symbolic regression called SR-R. At its core, SR-R employs a symbolic regression method based on Cartesian genetic programming to find a compact mathematical expression that accurately approximates the input-output relationship of a selected module within the NN. SR-R then replaces the targeted module with the discovered mathematical expression. Finally, SR-R fine-tunes the parameters of the remaining modules in the NN. Experiments are conducted on two types of NN benchmarks: multilayer perceptron NNs (MLP) and convolutional NNs (CNN). Experimental results show that, compared with NN pruning and NN distillation, SR-R can effectively reduce the number of NN parameters while maintaining or even enhancing inference accuracy.",
• notes = "GECCO-2025 RWA A Recombination of the 34th International Conference on Genetic Algorithms (ICGA) and the 30th Annual Genetic Programming Conference (GP)",

}

Genetic Programming entries for Wei Wei2 Qiang Lu Can Huang Jake Luo

Citations