AAAI 2025technical0 citations
Neuro-Guided Graph Search for Symbolic Regression (Student Abstract)
Piotr Wyrwiński, Krzysztof Krawiec
Abstract
This study introduces a neurosymbolic approach that performs iterative graph expansion guided by a graph neural network to solve symbolic regression problems. Empirical evaluation demonstrates superior performance of the method compared to baseline algorithms. We also integrate the method with an evolutionary algorithm, which results in further performance improvements.
BibTeX
@article{Wyrwiński_Krawiec_2025, title={Neuro-Guided Graph Search for Symbolic Regression (Student Abstract)}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/35314}, DOI={10.1609/aaai.v39i28.35314}, abstractNote={This study introduces a neurosymbolic approach that performs iterative graph expansion guided by a graph neural network to solve symbolic regression problems. Empirical evaluation demonstrates superior performance of the method compared to baseline algorithms. We also integrate the method with an evolutionary algorithm, which results in further performance improvements.}, number={28}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wyrwiński, Piotr and Krawiec, Krzysztof}, year={2025}, month={Apr.}, pages={29529-29531} }