On the Dynamics of Mating Preferences in Genetic Programming
José Maria Simões, Nuno Lourenço, Penousal Machado
TL;DR
The paper investigates how mating preferences evolve in Genetic Programming when implemented as Mating Preferences as Ideal Mating Partners (PIMP). By analyzing mutation variations (Subtree, Node Replacement, None) across symbolic regression tasks and a real-world diabetes dataset, it shows that preference dynamics are highly mutation-dependent: without depth-growth mutations, preferences tend to converge to single-node trees, whereas subtree mutation sustains diversity and yields smaller, more balanced trees. It also documents automatic role segregation (Choosers vs Courters) and generally higher diversity under PIMP compared to standard tournament selection, though mean fitness improvements are not guaranteed. These findings provide nuanced guidance on deploying PIMP for diversity and bloat control in GP and point to future work on broader benchmarks and alternative preference representations.
Abstract
Several mating restriction techniques have been implemented in Evolutionary Algorithms to promote diversity. From similarity-based selection to niche preservation, the general goal is to avoid premature convergence by not having fitness pressure as the single evolutionary force. In a way, such methods can resemble the mechanisms involved in Sexual Selection, although generally assuming a simplified approach. Recently, a selection method called mating Preferences as Ideal Mating Partners (PIMP) has been applied to GP, providing promising results both in performance and diversity maintenance. The method mimics Mate Choice through the unbounded evolution of personal preferences rather than having a single set of rules to shape parent selection. As such, PIMP allows ideal mate representations to evolve freely, thus potentially taking advantage of Sexual Selection as a dynamic secondary force to fitness pressure. However, it is still unclear how mating preferences affect the overall population and how dependent they are on set-up choices. In this work, we tracked the evolution of individual preferences through different mutation types, searching for patterns and evidence of self-reinforcement. Results suggest that mating preferences do not stand on their own, relying on subtree mutation to avoid convergence to single-node trees. Nevertheless, they consistently promote smaller and more balanced solutions depth-wise than a standard tournament selection, reducing the impact of bloat. Furthermore, when coupled with subtree mutation it also results in more solution diversity with statistically significant results.