Responsible Model Selection with Virny and VirnyView

Denys Herasymuk, Falaah Arif Khan, Julia Stoyanovich

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

    Abstract

    In this demonstration, we present a comprehensive software library for model auditing and responsible model selection, called Virny, along with an interactive tool called VirnyView. Our library is modular and extensible, it implements a rich set of performance and fairness metrics, including novel metrics that quantify and compare model stability and uncertainty, and enables performance analysis based on multiple sensitive attributes, and their intersections. The Virny library and the VirnyView tool are available at https://github.com/DataResponsibly/Virny and https://r-ai.co/VirnyView.

    Original languageEnglish (US)
    Title of host publicationSIGMOD-Companion 2024 - Companion of the 2024 International Conferaence on Management of Data
    PublisherAssociation for Computing Machinery
    Pages488-491
    Number of pages4
    ISBN (Electronic)9798400704222
    DOIs
    StatePublished - Jun 9 2024
    Event2024 International Conferaence on Management of Data, SIGMOD 2024 - Santiago, Chile
    Duration: Jun 9 2024Jun 15 2024

    Publication series

    NameProceedings of the ACM SIGMOD International Conference on Management of Data
    ISSN (Print)0730-8078

    Conference

    Conference2024 International Conferaence on Management of Data, SIGMOD 2024
    Country/TerritoryChile
    CitySantiago
    Period6/9/246/15/24

    Keywords

    • data-centric ai
    • fairness
    • model selection
    • robustness
    • stability

    ASJC Scopus subject areas

    • Software
    • Information Systems

    Fingerprint

    Dive into the research topics of 'Responsible Model Selection with Virny and VirnyView'. Together they form a unique fingerprint.

    Cite this