Scaling Genetic Programming to Large Datasets Using
Hierarchical Dynamic Subset Selection
IEEE Transactions on Systems, Man, and Cybernetics:
Part B - Cybernetics, 37 (4):
1065--1073 (August 2007)DOI: doi:10.1109/TSMCB.2007.896406
Abstract
The computational overhead of Genetic Programming (GP)
may be directly addressed without recourse to hardware
solutions using active learning algorithms based on the
Random or Dynamic Subset Selection heuristics (RSS or
DSS). This work begins by presenting a family of
hierarchical DSS algorithms: RSS-DSS, cascaded RSS-DSS,
and the Balanced Block DSS algorithm; where the latter
has not been previously introduced. Extensive
benchmarking over four unbalanced real-world binary
classification problems with 30,000 to 500,000 training
exemplars demonstrates that both the cascade and
Balanced Block algorithms are able to reduce the
likelihood of degenerates, whilst providing a
significant improvement in classification accuracy
relative to the original RSS-DSS algorithm. Moreover,
comparison with GP trained without an active learning
algorithm indicates that classification performance is
not compromised, while training is completed in minutes
as opposed to half a day.
Links and resources
Tags
community
@brazovayeye's tags highlighted