A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations

Josua Krause, Aritra Dasgupta, Jordan Swartz, Yindalon Aphinyanaphongs, Enrico Bertini

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

    Abstract

    Human-in-the-loop data analysis applications necessitate greater transparency in machine learning models for experts to understand and trust their decisions. To this end, we propose a visual analytics workflow to help data scientists and domain experts explore, diagnose, and understand the decisions made by a binary classifier. The approach leverages 'instance-level explanations', measures of local feature relevance that explain single instances, and uses them to build a set of visual representations that guide the users in their investigation. The workflow is based on three main visual representations and steps: one based on aggregate statistics to see how data distributes across correct / incorrect decisions; one based on explanations to understand which features are used to make these decisions; and one based on raw data, to derive insights on potential root causes for the observed patterns. The workflow is derived from a long-term collaboration with a group of machine learning and healthcare professionals who used our method to make sense of machine learning models they developed. The case study from this collaboration demonstrates that the proposed workflow helps experts derive useful knowledge about the model and the phenomena it describes, thus experts can generate useful hypotheses on how a model can be improved.

    Original languageEnglish (US)
    Title of host publication2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 - Proceedings
    EditorsTobias Schreck, Brian Fisher, Shixia Liu
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages162-172
    Number of pages11
    ISBN (Electronic)9781538631638
    DOIs
    StatePublished - Dec 21 2018
    Event2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 - Phoenix, United States
    Duration: Oct 1 2017Oct 6 2017

    Other

    Other2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017
    CountryUnited States
    CityPhoenix
    Period10/1/1710/6/17

    Fingerprint

    Classifiers
    Learning systems
    Transparency
    Statistics

    Keywords

    • Interpretation
    • Machine Learning
    • Visual Analytics

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Human-Computer Interaction
    • Information Systems
    • Media Technology

    Cite this

    Krause, J., Dasgupta, A., Swartz, J., Aphinyanaphongs, Y., & Bertini, E. (2018). A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations. In T. Schreck, B. Fisher, & S. Liu (Eds.), 2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 - Proceedings (pp. 162-172). [8585720] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VAST.2017.8585720

    A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations. / Krause, Josua; Dasgupta, Aritra; Swartz, Jordan; Aphinyanaphongs, Yindalon; Bertini, Enrico.

    2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 - Proceedings. ed. / Tobias Schreck; Brian Fisher; Shixia Liu. Institute of Electrical and Electronics Engineers Inc., 2018. p. 162-172 8585720.

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

    Krause, J, Dasgupta, A, Swartz, J, Aphinyanaphongs, Y & Bertini, E 2018, A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations. in T Schreck, B Fisher & S Liu (eds), 2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 - Proceedings., 8585720, Institute of Electrical and Electronics Engineers Inc., pp. 162-172, 2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017, Phoenix, United States, 10/1/17. https://doi.org/10.1109/VAST.2017.8585720
    Krause J, Dasgupta A, Swartz J, Aphinyanaphongs Y, Bertini E. A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations. In Schreck T, Fisher B, Liu S, editors, 2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 162-172. 8585720 https://doi.org/10.1109/VAST.2017.8585720
    Krause, Josua ; Dasgupta, Aritra ; Swartz, Jordan ; Aphinyanaphongs, Yindalon ; Bertini, Enrico. / A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations. 2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 - Proceedings. editor / Tobias Schreck ; Brian Fisher ; Shixia Liu. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 162-172
    @inproceedings{3febc12730b94a28a6fe6507190c1b30,
    title = "A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations",
    abstract = "Human-in-the-loop data analysis applications necessitate greater transparency in machine learning models for experts to understand and trust their decisions. To this end, we propose a visual analytics workflow to help data scientists and domain experts explore, diagnose, and understand the decisions made by a binary classifier. The approach leverages 'instance-level explanations', measures of local feature relevance that explain single instances, and uses them to build a set of visual representations that guide the users in their investigation. The workflow is based on three main visual representations and steps: one based on aggregate statistics to see how data distributes across correct / incorrect decisions; one based on explanations to understand which features are used to make these decisions; and one based on raw data, to derive insights on potential root causes for the observed patterns. The workflow is derived from a long-term collaboration with a group of machine learning and healthcare professionals who used our method to make sense of machine learning models they developed. The case study from this collaboration demonstrates that the proposed workflow helps experts derive useful knowledge about the model and the phenomena it describes, thus experts can generate useful hypotheses on how a model can be improved.",
    keywords = "Interpretation, Machine Learning, Visual Analytics",
    author = "Josua Krause and Aritra Dasgupta and Jordan Swartz and Yindalon Aphinyanaphongs and Enrico Bertini",
    year = "2018",
    month = "12",
    day = "21",
    doi = "10.1109/VAST.2017.8585720",
    language = "English (US)",
    pages = "162--172",
    editor = "Tobias Schreck and Brian Fisher and Shixia Liu",
    booktitle = "2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 - Proceedings",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - A Workflow for Visual Diagnostics of Binary Classifiers using Instance-Level Explanations

    AU - Krause, Josua

    AU - Dasgupta, Aritra

    AU - Swartz, Jordan

    AU - Aphinyanaphongs, Yindalon

    AU - Bertini, Enrico

    PY - 2018/12/21

    Y1 - 2018/12/21

    N2 - Human-in-the-loop data analysis applications necessitate greater transparency in machine learning models for experts to understand and trust their decisions. To this end, we propose a visual analytics workflow to help data scientists and domain experts explore, diagnose, and understand the decisions made by a binary classifier. The approach leverages 'instance-level explanations', measures of local feature relevance that explain single instances, and uses them to build a set of visual representations that guide the users in their investigation. The workflow is based on three main visual representations and steps: one based on aggregate statistics to see how data distributes across correct / incorrect decisions; one based on explanations to understand which features are used to make these decisions; and one based on raw data, to derive insights on potential root causes for the observed patterns. The workflow is derived from a long-term collaboration with a group of machine learning and healthcare professionals who used our method to make sense of machine learning models they developed. The case study from this collaboration demonstrates that the proposed workflow helps experts derive useful knowledge about the model and the phenomena it describes, thus experts can generate useful hypotheses on how a model can be improved.

    AB - Human-in-the-loop data analysis applications necessitate greater transparency in machine learning models for experts to understand and trust their decisions. To this end, we propose a visual analytics workflow to help data scientists and domain experts explore, diagnose, and understand the decisions made by a binary classifier. The approach leverages 'instance-level explanations', measures of local feature relevance that explain single instances, and uses them to build a set of visual representations that guide the users in their investigation. The workflow is based on three main visual representations and steps: one based on aggregate statistics to see how data distributes across correct / incorrect decisions; one based on explanations to understand which features are used to make these decisions; and one based on raw data, to derive insights on potential root causes for the observed patterns. The workflow is derived from a long-term collaboration with a group of machine learning and healthcare professionals who used our method to make sense of machine learning models they developed. The case study from this collaboration demonstrates that the proposed workflow helps experts derive useful knowledge about the model and the phenomena it describes, thus experts can generate useful hypotheses on how a model can be improved.

    KW - Interpretation

    KW - Machine Learning

    KW - Visual Analytics

    UR - http://www.scopus.com/inward/record.url?scp=85061067028&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85061067028&partnerID=8YFLogxK

    U2 - 10.1109/VAST.2017.8585720

    DO - 10.1109/VAST.2017.8585720

    M3 - Conference contribution

    AN - SCOPUS:85061067028

    SP - 162

    EP - 172

    BT - 2017 IEEE Conference on Visual Analytics Science and Technology, VAST 2017 - Proceedings

    A2 - Schreck, Tobias

    A2 - Fisher, Brian

    A2 - Liu, Shixia

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -