Title
Guiding Genetic Programming with Graph Neural Networks
Authors
[ 1 ] Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ 2 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ SzD ] doctoral school student | [ P ] employee
Scientific discipline (Law 2.0)
Year of publication
2024
Chapter type
chapter in monograph / paper
Publication language
english
Keywords
EN
- genetic programming
- symbolic regression
- graph neural networks
Abstract
EN In evolutionary computation, it is commonly assumed that a search algorithm acquires knowledge about a problem instance by sampling solutions from the search space and evaluating them with a fitness function. This is necessarily inefficient because fitness reveals very little about solutions - yet they contain more information that can be potentially exploited. To address this observation in genetic programming, we propose EvoNUDGE, which uses a graph neural network to elicit additional knowledge from symbolic regression problems. The network is queried on the problem before an evolutionary run to produce a library of subprograms, which is subsequently used to seed the initial population and bias the actions of search operators. In an extensive experiment on a large number of problem instances, EvoNUDGE is shown to significantly outperform multiple baselines, including the conventional tree-based genetic programming and the purely neural variant of the method.
Pages (from - to)
551 - 554
Ministry points / chapter
20
Ministry points / conference (CORE)
140
System created by Poznań University of Technology
and Poznan Supercomputing and Networking Center
Log in through eKonto to add to SIS