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

Lade...
Vorschaubild
Dateien
Zu diesem Dokument gibt es keine Dateien.
Datum
2020
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
Internationale Patentnummer
Angaben zur Forschungsförderung
European Union (EU): 825041
Projekt
SmartDataLake - Sustainable Data Lakes for Extreme-Scale Analytics
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
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.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690SPINNER, 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>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
URL der Originalveröffentl.
Prüfdatum der URL
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Ja
Diese Publikation teilen