RuleMatrix: Visualizing and Understanding Classifiers with Rules

Yao Ming, Huamin Qu, Enrico Bertini

    Research output: Contribution to journalArticle

    Abstract

    With the growing adoption of machine learning techniques, there is a surge of research interest towards making machine learning systems more transparent and interpretable. Various visualizations have been developed to help model developers understand, diagnose, and refine machine learning models. However, a large number of potential but neglected users are the domain experts with little knowledge of machine learning but are expected to work with machine learning systems. In this paper, we present an interactive visualization technique to help users with little expertise in machine learning to understand, explore and validate predictive models. By viewing the model as a black box, we extract a standardized rule-based knowledge representation from its input-output behavior. Then, we design RuleMatrix, a matrix-based visualization of rules to help users navigate and verify the rules and the black-box model. We evaluate the effectiveness of RuleMatrix via two use cases and a usability study.

    Original languageEnglish (US)
    JournalIEEE Transactions on Visualization and Computer Graphics
    DOIs
    StateAccepted/In press - Aug 17 2018

    Fingerprint

    Learning systems
    Classifiers
    Visualization
    Knowledge representation

    Keywords

    • explainable machine learning
    • rule visualization
    • visual analytics

    ASJC Scopus subject areas

    • Software
    • Signal Processing
    • Computer Vision and Pattern Recognition
    • Computer Graphics and Computer-Aided Design

    Cite this

    RuleMatrix : Visualizing and Understanding Classifiers with Rules. / Ming, Yao; Qu, Huamin; Bertini, Enrico.

    In: IEEE Transactions on Visualization and Computer Graphics, 17.08.2018.

    Research output: Contribution to journalArticle

    @article{fe05b368e4eb499fb5b5b6360c7eea2b,
    title = "RuleMatrix: Visualizing and Understanding Classifiers with Rules",
    abstract = "With the growing adoption of machine learning techniques, there is a surge of research interest towards making machine learning systems more transparent and interpretable. Various visualizations have been developed to help model developers understand, diagnose, and refine machine learning models. However, a large number of potential but neglected users are the domain experts with little knowledge of machine learning but are expected to work with machine learning systems. In this paper, we present an interactive visualization technique to help users with little expertise in machine learning to understand, explore and validate predictive models. By viewing the model as a black box, we extract a standardized rule-based knowledge representation from its input-output behavior. Then, we design RuleMatrix, a matrix-based visualization of rules to help users navigate and verify the rules and the black-box model. We evaluate the effectiveness of RuleMatrix via two use cases and a usability study.",
    keywords = "explainable machine learning, rule visualization, visual analytics",
    author = "Yao Ming and Huamin Qu and Enrico Bertini",
    year = "2018",
    month = "8",
    day = "17",
    doi = "10.1109/TVCG.2018.2864812",
    language = "English (US)",
    journal = "IEEE Transactions on Visualization and Computer Graphics",
    issn = "1077-2626",
    publisher = "IEEE Computer Society",

    }

    TY - JOUR

    T1 - RuleMatrix

    T2 - Visualizing and Understanding Classifiers with Rules

    AU - Ming, Yao

    AU - Qu, Huamin

    AU - Bertini, Enrico

    PY - 2018/8/17

    Y1 - 2018/8/17

    N2 - With the growing adoption of machine learning techniques, there is a surge of research interest towards making machine learning systems more transparent and interpretable. Various visualizations have been developed to help model developers understand, diagnose, and refine machine learning models. However, a large number of potential but neglected users are the domain experts with little knowledge of machine learning but are expected to work with machine learning systems. In this paper, we present an interactive visualization technique to help users with little expertise in machine learning to understand, explore and validate predictive models. By viewing the model as a black box, we extract a standardized rule-based knowledge representation from its input-output behavior. Then, we design RuleMatrix, a matrix-based visualization of rules to help users navigate and verify the rules and the black-box model. We evaluate the effectiveness of RuleMatrix via two use cases and a usability study.

    AB - With the growing adoption of machine learning techniques, there is a surge of research interest towards making machine learning systems more transparent and interpretable. Various visualizations have been developed to help model developers understand, diagnose, and refine machine learning models. However, a large number of potential but neglected users are the domain experts with little knowledge of machine learning but are expected to work with machine learning systems. In this paper, we present an interactive visualization technique to help users with little expertise in machine learning to understand, explore and validate predictive models. By viewing the model as a black box, we extract a standardized rule-based knowledge representation from its input-output behavior. Then, we design RuleMatrix, a matrix-based visualization of rules to help users navigate and verify the rules and the black-box model. We evaluate the effectiveness of RuleMatrix via two use cases and a usability study.

    KW - explainable machine learning

    KW - rule visualization

    KW - visual analytics

    UR - http://www.scopus.com/inward/record.url?scp=85051767155&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85051767155&partnerID=8YFLogxK

    U2 - 10.1109/TVCG.2018.2864812

    DO - 10.1109/TVCG.2018.2864812

    M3 - Article

    JO - IEEE Transactions on Visualization and Computer Graphics

    JF - IEEE Transactions on Visualization and Computer Graphics

    SN - 1077-2626

    ER -