Context Sight: Model Understanding and Debugging via Interpretable Context

Jun Yuan, Enrico Bertini

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

    Abstract

    Model interpretation is increasingly important for successful model development and deployment. In recent years, many explanation methods are introduced to help humans understand how a machine learning model makes a decision on a specific instance. Recent studies show that contextualizing an individual model decision within a set of relevant examples can improve the model understanding. However, there is a lack of systematic study on what factors are considered when generating and using the context examples to explain model predictions, and how context examples help with model understanding and debugging in practice. In this work, we first identify a taxonomy of context generation and summarization through literature review. We then present Context Sight, a visual analytics system that integrates customized context generation and multiple-level context summarization to assist context exploration and interpretation. We evaluate the usefulness of the system through a detailed use case. This work is an initial step for a set of systematic research on how contextualization can help data scientists and practitioners understand and diagnose model behaviors, based on which we will gain a better understanding of the usage of context.

    Original languageEnglish (US)
    Title of host publicationProceedings of the Workshop on Human-In-the-Loop Data Analytics, HILDA 2022
    PublisherAssociation for Computing Machinery, Inc
    ISBN (Electronic)9781450394420
    DOIs
    StatePublished - Jun 12 2022
    Event2022 Workshop on Human-In-the-Loop Data Analytics, HILDA 2022 - Co-located with SIGMOD 2022 - Philadelphia, United States
    Duration: Jun 12 2022 → …

    Publication series

    NameProceedings of the Workshop on Human-In-the-Loop Data Analytics, HILDA 2022

    Conference

    Conference2022 Workshop on Human-In-the-Loop Data Analytics, HILDA 2022 - Co-located with SIGMOD 2022
    Country/TerritoryUnited States
    CityPhiladelphia
    Period6/12/22 → …

    Keywords

    • contextualization
    • explainable AI
    • model debugging
    • model understanding
    • visual analytics

    ASJC Scopus subject areas

    • Computational Theory and Mathematics
    • Computer Science Applications
    • Information Systems

    Fingerprint

    Dive into the research topics of 'Context Sight: Model Understanding and Debugging via Interpretable Context'. Together they form a unique fingerprint.

    Cite this