explAIner : A Visual Analytics Framework for Interactive and Explainable Machine Learning

Spinner, Thilo; Schlegel, Udo; Schäfer, Hanna; El-Assady, Mennatallah

explAIner : A Visual Analytics Framework for Interactive and Explainable Machine Learning

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

2020

Angaben zur Forschungsförderung

European Union (EU): 825041

Projekt

SmartDataLake - Sustainable Data Lakes for Extreme-Scale Analytics

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Zeitschriftenartikel

Publikationsstatus

Published

Erschienen in

IEEE Transactions on Visualization and Computer Graphics. Institute of Electrical and Electronics Engineers (IEEE). 2020, 26(1), pp. 1064-1074. ISSN 1077-2626. eISSN 1941-0506. Available under: doi: 10.1109/TVCG.2019.2934629

Zusammenfassung

We propose a framework for interactive and explainable machine learning that enables users to (1) understand machine learning models; (2) diagnose model limitations using different explainable AI methods; as well as (3) refine and optimize the models. Our framework combines an iterative XAI pipeline with eight global monitoring and steering mechanisms, including quality monitoring, provenance tracking, model comparison, and trust building. To operationalize the framework, we present explAIner, a visual analytics system for interactive and explainable machine learning that instantiates all phases of the suggested pipeline within the commonly used TensorBoard environment. We performed a user-study with nine participants across different expertise levels to examine their perception of our workflow and to collect suggestions to fill the gap between our system and framework. The evaluation confirms that our tightly integrated system leads to an informed machine learning process while disclosing opportunities for further extensions.

Fachgebiet (DDC)

004 Informatik

Zitieren

ISO 690

SPINNER, Thilo, Udo SCHLEGEL, Hanna SCHÄFER, Mennatallah EL-ASSADY, 2020. explAIner : A Visual Analytics Framework for Interactive and Explainable Machine Learning. In: IEEE Transactions on Visualization and Computer Graphics. Institute of Electrical and Electronics Engineers (IEEE). 2020, 26(1), pp. 1064-1074. ISSN 1077-2626. eISSN 1941-0506. Available under: doi: 10.1109/TVCG.2019.2934629

BibTex

@article{Spinner2020-01explA-49045,
  year={2020},
  doi={10.1109/TVCG.2019.2934629},
  title={explAIner : A Visual Analytics Framework for Interactive and Explainable Machine Learning},
  number={1},
  volume={26},
  issn={1077-2626},
  journal={IEEE Transactions on Visualization and Computer Graphics},
  pages={1064--1074},
  author={Spinner, Thilo and Schlegel, Udo and Schäfer, Hanna and El-Assady, Mennatallah}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/49045">
    <dc:creator>Spinner, Thilo</dc:creator>
    <dcterms:title>explAIner : A Visual Analytics Framework for Interactive and Explainable Machine Learning</dcterms:title>
    <dc:contributor>Schlegel, Udo</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Schlegel, Udo</dc:creator>
    <dc:contributor>Schäfer, Hanna</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-03-13T13:51:23Z</dc:date>
    <dc:creator>Schäfer, Hanna</dc:creator>
    <dc:contributor>Spinner, Thilo</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/49045"/>
    <dcterms:issued>2020-01</dcterms:issued>
    <dc:creator>El-Assady, Mennatallah</dc:creator>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>El-Assady, Mennatallah</dc:contributor>
    <dcterms:abstract xml:lang="eng">We propose a framework for interactive and explainable machine learning that enables users to (1) understand machine learning models; (2) diagnose model limitations using different explainable AI methods; as well as (3) refine and optimize the models. Our framework combines an iterative XAI pipeline with eight global monitoring and steering mechanisms, including quality monitoring, provenance tracking, model comparison, and trust building. To operationalize the framework, we present explAIner, a visual analytics system for interactive and explainable machine learning that instantiates all phases of the suggested pipeline within the commonly used TensorBoard environment. We performed a user-study with nine participants across different expertise levels to examine their perception of our workflow and to collect suggestions to fill the gap between our system and framework. The evaluation confirms that our tightly integrated system leads to an informed machine learning process while disclosing opportunities for further extensions.</dcterms:abstract>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-03-13T13:51:23Z</dcterms:available>
    <dc:language>eng</dc:language>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja

Begutachtet

Ja