User-based active learning

Christin Seifert, Michael Granitzer

    Research output: Chapter in Book/Report/Conference proceedingChapterAcademicpeer-review

    22 Citations (Scopus)

    Abstract

    Active learning has been proven a reliable strategy to reduce manual efforts in training data labeling. Such strategies incorporate the user as oracle: the classifier selects the most appropriate example and the user provides the label. While this approach is tailored towards the classifier, more intelligent input from the user may be beneficial. For instance, given only one example at a time users are hardly able to determine whether this example is an outlier or not. In this paper we propose user-based visually-supported active learning strategies that allow the user to do both, selecting and labeling examples given a trained classifier. While labeling is straightforward, selection takes place using a interactive visualization of the classifier's a-posteriori output probabilities. By simulating different user selection strategies we show, that user-based active learning outperforms uncertainty based sampling methods and yields a more robust approach on different data sets. The obtained results point towards the potential of combining active learning strategies with results from the field of information visualization.
    Original languageEnglish
    Title of host publicationProceedings - IEEE International Conference on Data Mining, ICDM
    Place of PublicationPiscataway, NJ
    PublisherIEEE
    Pages418-425
    Number of pages8
    ISBN (Electronic)978-0-7695-4257-7
    ISBN (Print)978-1-4244-9244-2
    DOIs
    Publication statusPublished - 2010
    EventIEEE International Conference on Data Mining, ICDM 2010 - Sydney, Australia
    Duration: 13 Dec 201013 Dec 2010

    Publication series

    NameProceedings IEEE International Conference on Data Mining (ICDM)
    PublisherIEEE
    Volume2010
    ISSN (Print)2375-9232
    ISSN (Electronic)2375-9259

    Conference

    ConferenceIEEE International Conference on Data Mining, ICDM 2010
    Abbreviated titleICDM
    Country/TerritoryAustralia
    CitySydney
    Period13/12/1013/12/10

    Keywords

    • Active learning
    • Information visualization
    • User behavior
    • Visualization

    Fingerprint

    Dive into the research topics of 'User-based active learning'. Together they form a unique fingerprint.

    Cite this