Feature selection via dependence maximization

Le Song*, Alex Smola, Arthur Gretton, Justin Bedo, Karsten Borgwardt

*Corresponding author for this work

    Research output: Contribution to journalArticlepeer-review

    318 Citations (Scopus)

    Abstract

    We introduce a framework for feature selection based on dependence maximization between the selected features and the labels of an estimation problem, using the Hilbert-Schmidt Independence Criterion. The key idea is that good features should be highly dependent on the labels. Our approach leads to a greedy procedure for feature selection. We show that a number of existing feature selectors are special cases of this framework. Experiments on both artificial and real-world data show that our feature selector works well in practice.

    Original languageEnglish
    Pages (from-to)1393-1434
    Number of pages42
    JournalJournal of Machine Learning Research
    Volume13
    Publication statusPublished - May 2012

    Fingerprint

    Dive into the research topics of 'Feature selection via dependence maximization'. Together they form a unique fingerprint.

    Cite this