Time Series Model Attribution Visualizations as Explanations

Schlegel, Udo; Keim, Daniel A.

Time Series Model Attribution Visualizations as Explanations

Dateien

Schlegel_2-eel2423v2fnx8.pdfGröße: 233.89 KBDownloads: 41

Datum

2021

Open Access-Veröffentlichung

Open Access Green

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Beitrag zu einem Konferenzband

Publikationsstatus

Published

Erschienen in

2021 IEEE Workshop on TRust and EXpertise in Visual Analytics (TREX). Piscataway, NJ: IEEE, 2021, pp. 27-31. ISBN 978-1-6654-1817-1. Available under: doi: 10.1109/TREX53765.2021.00010

Zusammenfassung

Attributions are a common local explanation technique for deep learning models on single samples as they are easily extractable and demonstrate the relevance of input values. In many cases, heatmaps visualize such attributions for samples, for instance, on images. However, heatmaps are not always the ideal visualization to explain certain model decisions for other data types. In this review, we focus on attribution visualizations for time series. We collect attribution heatmap visualizations and some alternatives, discuss the advantages as well as disadvantages and give a short position towards future opportunities for attributions and explanations for time series.

Fachgebiet (DDC)

004 Informatik

Konferenz

2021 IEEE Workshop on TRust and EXpertise in Visual Analytics (TREX), 24. Okt. 2021 - 25. Okt. 2021, New Orleans, LA

Zitieren

ISO 690

SCHLEGEL, Udo, Daniel A. KEIM, 2021. Time Series Model Attribution Visualizations as Explanations. 2021 IEEE Workshop on TRust and EXpertise in Visual Analytics (TREX). New Orleans, LA, 24. Okt. 2021 - 25. Okt. 2021. In: 2021 IEEE Workshop on TRust and EXpertise in Visual Analytics (TREX). Piscataway, NJ: IEEE, 2021, pp. 27-31. ISBN 978-1-6654-1817-1. Available under: doi: 10.1109/TREX53765.2021.00010

BibTex

@inproceedings{Schlegel2021-09-27T10:44:07ZSerie-55189,
  year={2021},
  doi={10.1109/TREX53765.2021.00010},
  title={Time Series Model Attribution Visualizations as Explanations},
  isbn={978-1-6654-1817-1},
  publisher={IEEE},
  address={Piscataway, NJ},
  booktitle={2021 IEEE Workshop on TRust and EXpertise in Visual Analytics (TREX)},
  pages={27--31},
  author={Schlegel, Udo and Keim, Daniel A.}
}

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/123456789/55189">
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:abstract xml:lang="eng">Attributions are a common local explanation technique for deep learning models on single samples as they are easily extractable and demonstrate the relevance of input values. In many cases, heatmaps visualize such attributions for samples, for instance, on images. However, heatmaps are not always the ideal visualization to explain certain model decisions for other data types. In this review, we focus on attribution visualizations for time series. We collect attribution heatmap visualizations and some alternatives, discuss the advantages as well as disadvantages and give a short position towards future opportunities for attributions and explanations for time series.</dcterms:abstract>
    <dc:contributor>Schlegel, Udo</dc:contributor>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/55189/1/Schlegel_2-eel2423v2fnx8.pdf"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/55189"/>
    <dcterms:title>Time Series Model Attribution Visualizations as Explanations</dcterms:title>
    <dc:language>eng</dc:language>
    <dcterms:issued>2021-09-27T10:44:07Z</dcterms:issued>
    <dc:contributor>Keim, Daniel A.</dc:contributor>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-10-08T08:45:54Z</dc:date>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-10-08T08:45:54Z</dcterms:available>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/55189/1/Schlegel_2-eel2423v2fnx8.pdf"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Keim, Daniel A.</dc:creator>
    <dc:creator>Schlegel, Udo</dc:creator>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja