Evolving Form and Function: Dual-Objective Optimization in Neural Symbolic Regression Networks

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

@InProceedings{bertschinger:2024:GECCO,

• author = "Amanda Bertschinger and James Bagrow and Joshua Bongard",
• title = "Evolving Form and Function: Dual-Objective Optimization in Neural Symbolic Regression Networks",
• booktitle = "Proceedings of the 2024 Genetic and Evolutionary Computation Conference",
• year = "2024",
• editor = "Jean-Baptiste Mouret and Kai Qin and Julia Handl and Xiaodong Li and Markus Wagner and Mario Garza-Fabre and Kate Smith-Miles and Richard Allmendinger and Ying Bi and Grant Dick and Amir H Gandomi and Marcella Scoczynski Ribeiro Martins and Hirad Assimi and Nadarajen Veerapen and Yuan Sun and Mario Andres Munyoz and Ahmed Kheiri and Nguyen Su and Dhananjay Thiruvady and Andy Song and Frank Neumann and Carla Silva",
• pages = "277--285",
• address = "Melbourne, Australia",
• series = "GECCO '24",
• month = "14-18 " # jul,
• organisation = "SIGEVO",
• publisher = "Association for Computing Machinery",
• publisher_address = "New York, NY, USA",
• keywords = "genetic algorithms, genetic programming, symbolic regression, neuroevolution, multi-objective optimization, Evolutionary Machine Learning",
• isbn13 = "979-8-4007-0494-9",
• DOI = "doi:10.1145/3638529.3654030",
• size = "9 pages",
• abstract = "Data increasingly abounds, but distilling their underlying relationships down to something interpretable remains challenging. One approach is genetic programming, which 'symbolically regresses' a data set down into an equation. However, symbolic regression (SR) faces the issue of requiring training from scratch for each new dataset. To generalize across all datasets, deep learning techniques have been applied to SR. These networks, however, are only able to be trained using a symbolic objective: NN-generated and target equations are symbolically compared. But this does not consider the predictive power of these equations, which could be measured by a behavioral objective that compares the generated equation's predictions to actual data. Here we introduce a method that combines gradient descent and evolutionary computation to yield neural networks that minimize the symbolic and behavioral errors of the equations they generate from data. As a result, these evolved networks are shown to generate more symbolically and behaviorally accurate equations than those generated by networks trained by state-of-the-art gradient based neural symbolic regression methods. We hope this method suggests that evolutionary algorithms, combined with gradient descent, can improve SR results by yielding equations with more accurate form and function.",
• notes = "GECCO-2024 EML A Recombination of the 33rd International Conference on Genetic Algorithms (ICGA) and the 29th Annual Genetic Programming Conference (GP)",

}

Genetic Programming entries for Amanda Bertschinger James Bagrow Josh C Bongard

Citations