One Tree to Explain Them All

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@InProceedings{Johansson:2011:OTtETA,
  title =        "One Tree to Explain Them All",
  author =       "Ulf Johansson and Cecilia Sonstrod and Tuve Lofstrom",
  pages =        "1444--1451",
  booktitle =    "Proceedings of the 2011 IEEE Congress on Evolutionary
                 Computation",
  year =         "2011",
  editor =       "Alice E. Smith",
  month =        "5-8 " # jun,
  address =      "New Orleans, USA",
  organization = "IEEE Computational Intelligence Society",
  publisher =    "IEEE Press",
  ISBN =         "0-7803-8515-2",
  keywords =     "genetic algorithms, genetic programming,
                 Classification, clustering, data analysis and data
                 mining, Learning classifier systems",
  DOI =          "doi:10.1109/CEC.2011.5949785",
  size =         "8 pages",
  abstract =     "Random forest is an often used ensemble technique,
                 renowned for its high predictive performance. Random
                 forests models are, however, due to their sheer
                 complexity inherently opaque, making human
                 interpretation and analysis impossible. This paper
                 presents a method of approximating the random forest
                 with just one decision tree. The approach uses oracle
                 coaching, a recently suggested technique where a weaker
                 but transparent model is generated using combinations
                 of regular training data and test data initially
                 labelled by a strong classifier, called the oracle. In
                 this study, the random forest plays the part of the
                 oracle, while the transparent models are decision trees
                 generated by either the standard tree inducer J48, or
                 by evolving genetic programs. Evaluation on 30 data
                 sets from the UCI repository shows that oracle coaching
                 significantly improves both accuracy and area under ROC
                 curve, compared to using training data only. As a
                 matter of fact, resulting single tree models are as
                 accurate as the random forest, on the specific test
                 instances. Most importantly, this is not achieved by
                 inducing or evolving huge trees having perfect
                 fidelity; a large majority of all trees are instead
                 rather compact and clearly comprehensible. The
                 experiments also show that the evolution outperformed
                 J48, with regard to accuracy, but that this came at the
                 expense of slightly larger trees.",
  notes =        "CEC2011 sponsored by the IEEE Computational
                 Intelligence Society, and previously sponsored by the
                 EPS and the IET.",
}

Genetic Programming entries for Ulf Johansson Cecilia Sonstrod Tuve Lofstrom

Citations