On the Dynamics of Mating Preferences in Genetic Programming

2025-04-08

AI Summary

This work investigates the dynamic evolution of mating preferences—modeled as a sexual selection analog—in genetic programming (GP), focusing on their role in mitigating premature convergence and bloat. We propose a modeling framework based on PIMP (Preference-as-Ideal-Mating-Partner) to systematically trace how individual mating preferences evolve under subtree mutation—a first in GP literature. Our analysis reveals that preferences self-reinforce exclusively under subtree mutation, suppress single-node degeneration, and promote balanced program depth and enhanced population diversity. Compared to standard tournament selection, our mechanism significantly reduces mean program depth (p < 0.01), effectively curbs code bloat, and yields statistically significant improvements in population diversity (p < 0.05). The core contribution lies in demonstrating that mating preferences do not operate in isolation but co-adapt with specific mutation operators and fitness-based selection—thereby providing both theoretical grounding and empirical validation for integrating sexual selection mechanisms into GP.

Technology Category

• Search and Optimization: Evolutionary Computation
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments

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.

Problem

• How mating preferences impact population dynamics in Genetic Programming
• Dependence of mating preferences on setup choices in evolution
• Effect of mating preferences on solution diversity and bloat reduction

Innovation

• Mating Preferences as Ideal Mating Partners (PIMP)
• Unbounded evolution of personal preferences
• Coupling with subtree mutation for diversity