Time Series Model Attribution Visualizations as Explanations

Thumbnail Image
Files
Schlegel_2-eel2423v2fnx8.pdf(233.89 KB)
Date
2021
Authors
Editors
Contact
Journal ISSN
Electronic ISSN
ISBN
Bibliographical data
Publisher
Series
URI (citable link)
urn:nbn:de:bsz:352-2-eel2423v2fnx8
DOI (citable link)
10.1109/TREX53765.2021.00010
ArXiv-ID
2109.12935
International patent number
Link to the license
In Copyright
EU project number
Project
Open Access publication
Collections
Informatik und Informationswissenschaft
Restricted until
Title in another language
Research Projects
Organizational Units
Journal Issue
Publication type
Contribution to a conference collection
Publication status
Published
Published 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
Abstract
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.
Summary in another language
Subject (DDC)
004 Computer Science
Keywords
Conference
2021 IEEE Workshop on TRust and EXpertise in Visual Analytics (TREX), Oct 24, 2021 - Oct 25, 2021, New Orleans, LA
Review
undefined / . - undefined, undefined. - (undefined; undefined)
Cite This
ISO 690SCHLEGEL, 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, Oct 24, 2021 - Oct 25, 2021. In: 2021 IEEE Workshop on TRust and EXpertise in Visual Analytics (TREX). Piscataway, NJ:IEEE, 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>
Internal note
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Contact
URL of original publication
Test date of URL
Examination date of dissertation
Method of financing
Comment on publication
Alliance license
Corresponding Authors der Uni Konstanz vorhanden
International Co-Authors
Bibliography of Konstanz
Yes
Refereed