We introduce in this paper a runtime-efficient tree hashing algorithm for the identification of isomorphic subtrees, with two important applications in genetic programming for symbolic regression: fast, online calculation of population diversity and algebraic simplification of symbolic expression trees. Based on this hashing approach, we propose a simple diversity-preservation mechanism with promising results on a collection of symbolic regression benchmark problems.
@article{arxiv.2107.10640,
title = {Hash-Based Tree Similarity and Simplification in Genetic Programming for Symbolic Regression},
author = {Bogdan Burlacu and Lukas Kammerer and Michael Affenzeller and Gabriel Kronberger},
journal= {arXiv preprint arXiv:2107.10640},
year = {2021}
}
Comments
International Conference on Computer Aided Systems Theory, EUROCAST 2019