Embedding Monte Carlo Search of Features in Tree-Based Ensemble Methods

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@InProceedings{DBLP:conf/pkdd/MaesGW12,

• author = "Francis Maes and Pierre Geurts and Louis Wehenkel",
• title = "Embedding Monte Carlo Search of Features in Tree-Based Ensemble Methods",
• booktitle = "European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2012, Part I",
• year = "2012",
• editor = "Peter A. Flach and Tijl {De Bie} and Nello Cristianini",
• pages = "191--206",
• volume = "7523",
• series = "Lecture Notes in Computer Science",
• bibsource = "DBLP, http://dblp.uni-trier.de",
• address = "Bristol UK",
• month = "24-28 " # sep,
• publisher = "Springer",
• keywords = "genetic algorithms, genetic programming, MCTS, Dimensionality Reduction, Feature Selection and Extraction, Embedded Feature Generation, Monte Carlo Search, Decision Trees, Random Forests, Tree Boosting",
• isbn13 = "978-3-642-33459-7",
• DOI = "doi:10.1007/978-3-642-33460-3_18",
• size = "16 pages",
• abstract = "Feature generation is the problem of automatically constructing good features for a given target learning problem. While most feature generation algorithms belong either to the filter or to the wrapper approach, this paper focuses on embedded feature generation. We propose a general scheme to embed feature generation in a wide range of tree-based learning algorithms, including single decision trees, random forests and tree boosting. It is based on the formalisation of feature construction as a sequential decision making problem addressed by a tractable Monte Carlo search algorithm coupled with node splitting. This leads to fast algorithms that are applicable to large-scale problems. We empirically analyse the performances of these tree-based learners combined or not with the feature generation capability on several standard datasets.",
• notes = "

  Feature engineering - the process of identifying a good set of features for a given learning task.

  reverse polish notation RPN grammar postfix. vowel, segment, spambase, satellite, pendigits, dig44. Baseline, random, step, look-ahead. tree stumps variance.

  www.ecmlpkdd2012.net/files/2012/09/ECMLPKDD2012booklet.pdf",

}

Genetic Programming entries for Francis Maes Pierre Geurts Louis Wehenkel

Citations