Modeling XCS in class imbalances: Population size and parameter settings
1 February 2007Orriols-Puig A., Goldberg D. E., Sastry K., Bernadó-Mansilla E. (2007). IlliGAL Report No. 2007001. University of Illinois at Urbana-Champaign, Urbana IL. [Full paper - PDF] [Full paper - PS].
Abstract:
This paper analyzes the scalability of the population size required in XCS to maintain niches that are infrequently activated. Facetwise models have been developed to predict the effect of the imbalance ratio—ratio between the number of instances of the majority class and the minority class that are sampled to XCS—on population initialization, and on the creation and deletion of classifiers of the minority class. While theoretical models show that, ideally, XCS scales linearly with the imbalance ratio, XCS with standard configuration scales exponentially. The causes that are potentially responsible for this deviation from the ideal scalability are also investigated. Specifically, the inheritance procedure of classifiers’ parameters, mutation, and subsumption are analyzed, and improvements in XCS’s mechanisms are proposed to effectively and efficiently handle imbalanced problems. Once the recommendations are incorporated to XCS, empirical results show that the population size in XCS indeed scales linearly with the imbalance ratio.
Related Posts:
- Modeling XCS in class imbalances: Population sizing and parameter settings
- Population sizing to go: Online adaptation using noise and substructural measurement
- Online population size adjusting using noise and substructural measurements
- Modeling tournament selection with replacement using apparent added noise
- Tournament selection in XCS
No comments yet
