Speculative Execution for Guided Visual Analytics

Sperrle, Fabian; Bernard, Jürgen; Sedlmair, Michael; Keim, Daniel A.; El-Assady, Mennatallah

Speculative Execution for Guided Visual Analytics

Files

Sperrle_2-1vfpbv3lvivg2.pdf(1.24 MB)

Date

2018

Authors

Sperrle, Fabian

Bernard, Jürgen

Sedlmair, Michael

Keim, Daniel A.

El-Assady, Mennatallah

Publication type

Contribution to a conference collection

Publication status

Published

Published in

Workshop for Machine Learning from User Interaction for Visualization and Analytics at IEEE VIS

Abstract

We propose the concept of Speculative Execution for Visual Analytics and discuss its effectiveness for model exploration and optimization. Speculative Execution enables the automatic generation of alternative, competing model configurations that do not alter the current model state unless explicitly confirmed by the user. These alternatives are computed based on either user interactions or model quality measures and can be explored using delta-visualizations. By automatically proposing modeling alternatives, systems employing Speculative Execution can shorten the gap between users and models, reduce the confirmation bias and speed up optimization processes. In this paper, we have assembled five application scenarios showcasing the potential of Speculative Execution, as well as a potential for further research.

Subject (DDC)

004 Computer Science

Conference

Workshop for Machine Learning from User Interaction for Visualization and Analytics at IEEE VIS, Oct 22, 2018, Berlin

Cite This

ISO 690

SPERRLE, Fabian, Jürgen BERNARD, Michael SEDLMAIR, Daniel A. KEIM, Mennatallah EL-ASSADY, 2018. Speculative Execution for Guided Visual Analytics. Workshop for Machine Learning from User Interaction for Visualization and Analytics at IEEE VIS. Berlin, Oct 22, 2018. In: Workshop for Machine Learning from User Interaction for Visualization and Analytics at IEEE VIS

BibTex

@inproceedings{Sperrle2018Specu-45049,
  year={2018},
  title={Speculative Execution for Guided Visual Analytics},
  url={https://scibib.dbvis.de/publications/view/774},
  booktitle={Workshop for Machine Learning from User Interaction for Visualization and Analytics at IEEE VIS},
  author={Sperrle, Fabian and Bernard, Jürgen and Sedlmair, Michael and Keim, Daniel A. 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/123456789/45049">
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-02-14T15:11:41Z</dcterms:available>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/45049/1/Sperrle_2-1vfpbv3lvivg2.pdf"/>
    <dc:language>eng</dc:language>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-02-14T15:11:41Z</dc:date>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:issued>2018</dcterms:issued>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Bernard, Jürgen</dc:creator>
    <dc:contributor>Sedlmair, Michael</dc:contributor>
    <dc:rights>terms-of-use</dc:rights>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:contributor>Sperrle, Fabian</dc:contributor>
    <dc:creator>Sedlmair, Michael</dc:creator>
    <dc:creator>Keim, Daniel A.</dc:creator>
    <dc:contributor>Keim, Daniel A.</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/45049"/>
    <dc:contributor>Bernard, Jürgen</dc:contributor>
    <dc:creator>Sperrle, Fabian</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>El-Assady, Mennatallah</dc:creator>
    <dcterms:abstract xml:lang="eng">We propose the concept of Speculative Execution for Visual Analytics and discuss its effectiveness for model exploration and optimization. Speculative Execution enables the automatic generation of alternative, competing model configurations that do not alter the current model state unless explicitly confirmed by the user. These alternatives are computed based on either user interactions or model quality measures and can be explored using delta-visualizations. By automatically proposing modeling alternatives, systems employing Speculative Execution can shorten the gap between users and models, reduce the confirmation bias and speed up optimization processes. In this paper, we have assembled five application scenarios showcasing the potential of Speculative Execution, as well as a potential for further research.</dcterms:abstract>
    <dcterms:title>Speculative Execution for Guided Visual Analytics</dcterms:title>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>El-Assady, Mennatallah</dc:contributor>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/45049/1/Sperrle_2-1vfpbv3lvivg2.pdf"/>
  </rdf:Description>
</rdf:RDF>

URL of original publication

https://scibib.dbvis.de/publications/view/774

Test date of URL

2019-02-14

Bibliography of Konstanz

Yes