Guiding Genetic Programming with Graph Neural Networks
This addresses a bottleneck in evolutionary computation for symbolic regression, offering a novel hybrid approach that is incremental but shows strong gains.
The paper tackled the inefficiency of genetic programming in symbolic regression by proposing EvoNUDGE, which uses a graph neural network to extract knowledge from problems and guide evolution, resulting in significant performance improvements over multiple baselines.
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.