Recursive Feature Elimination by Sensitivity Testing

Nicholas Sean Escanilla, Lisa Hellerstein, Ross Kleiman, Zhaobin Kuang, James Shull, David Page

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    There is great interest in methods to improve human insight into trained non-linear models. Leading approaches include producing a ranking of the most relevant features, a non-trivial task for non-linear models. We show theoretically and empirically the benefit of a novel version of recursive feature elimination (RFE) as often used with SVMs; the key idea is a simple twist on the kinds of sensitivity testing employed in computational learning theory with membership queries (e.g., [1]). With membership queries, one can check whether changing the value of a feature in an example changes the label. In the real-world, we usually cannot get answers to such queries, so our approach instead makes these queries to a trained (imperfect) non-linear model. Because SVMs are widely used in bioinformatics, our empirical results use a real-world cancer genomics problem; because ground truth is not known for this task, we discuss the potential insights provided. We also evaluate on synthetic data where ground truth is known.

    Original languageEnglish (US)
    Title of host publicationProceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018
    EditorsM. Arif Wani, Moamar Sayed-Mouchaweh, Edwin Lughofer, Joao Gama, Mehmed Kantardzic
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages40-47
    Number of pages8
    ISBN (Electronic)9781538668047
    DOIs
    StatePublished - Jul 2 2018
    Event17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018 - Orlando, United States
    Duration: Dec 17 2018Dec 20 2018

    Publication series

    NameProceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018

    Conference

    Conference17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018
    Country/TerritoryUnited States
    CityOrlando
    Period12/17/1812/20/18

    Keywords

    • Correlation immunity
    • Feature ranking
    • Feature selection
    • Machine learning

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Networks and Communications
    • Computer Science Applications
    • Computer Vision and Pattern Recognition
    • Safety, Risk, Reliability and Quality
    • Signal Processing
    • Decision Sciences (miscellaneous)

    Fingerprint

    Dive into the research topics of 'Recursive Feature Elimination by Sensitivity Testing'. Together they form a unique fingerprint.

    Cite this