Guiding Genetic Programming with Graph Neural Networks

TL;DR

This paper introduces EvoNUDGE, a novel approach that leverages graph neural networks to enhance genetic programming by extracting and utilizing problem-specific knowledge, leading to improved search efficiency and performance.

Contribution

EvoNUDGE is the first method to integrate graph neural networks for knowledge elicitation in genetic programming, significantly improving solution quality over traditional methods.

Findings

EvoNUDGE outperforms baseline genetic programming methods.

The approach effectively uses problem-specific knowledge to guide search.

Significant performance gains across diverse symbolic regression problems.

Abstract

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.