The Role of Mate Selection in Genetic Algorithms

Organized by the Complex Systems Modeling Research Focus Area of the Modeling, Algorithms, and Informatics Group (CCS-3).

Chien-feng Huang, Department of Electrical Engineering and Computer Science, University of Michigan.

January 9th, ACL West Conference Room, TA-3, Building 200, 2:30-4:00pm.

The process of information exchange among the population of individuals manipulated by Genetic Algorithms (GAs) involves two key components: crossover and mate selection. The central theme of my thesis concentrates on the investigation of effects of "mate selection" in GAs. The prevalence of mate selection in biology is widely recognized, yet a systematic investigation of this subject in GA research is still lacking. The goal of my work is to propose a framework that facilitates exploration of this direction.

In this talk, I'll present motivations for this work, and describe investigations of the basic properties of mate selection in the context of GA. Then I'll discuss my study based on two classes of more complicated, building-block-based problems---the Royal Road functions and the hyperplane-defined functions. With the results obtained, I introduce an important hypothesis regarding the role of mate selection in GAs. That is, if one's goal is to improve the GA's search for best-so-far solutions, then on easy problems a dissimilarity-based mate selection scheme is more beneficial. If problems present sufficient difficulty, the GA's search power can be further improved by reducing the selection pressure toward higher-fitness individuals while selecting mates.

I'll discuss how this hypothesis is validated based on several more realistic, non-building-block-based benchmark testbeds. The encouraging results imply that the ideas of mate selection proposed can be applied to practical problems. I will also discuss a more general setting in the context of multimodal function optimization, where identifying multiple peaks and maintaining subpopulations of the search space are two central themes. An immune system model is employed to study these two problems. The experimental results indeed shed more light on how mate selection schemes compare to traditional selection schemes. Finally, I'll discuss how mate selection can fit in the framework of contextual genetic algorithms.

Related Links

For more information contact Luis Rocha at
Last Modified: January 7, 2002