Type of Publication: | Contribution to a conference collection |
Publication status: | Published |
URI (citable link): | http://nbn-resolving.de/urn:nbn:de:bsz:352-2-1iaybk1cefn2y7 |
Author: | Schlegel, Udo; Arnout, Hiba; El-Assady, Mennatallah; Oelke, Daniela; Keim, Daniel A. |
Year of publication: | 2019 |
Conference: | 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), Oct 27, 2019 - Oct 28, 2019, Seoul, Korea (South) |
Published in: | 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). - Piscataway, NJ : IEEE, 2019. - pp. 4321-4325. - ISSN 2473-9936. - eISSN 2473-9944. - ISBN 978-1-72815-023-9 |
DOI (citable link): | https://dx.doi.org/10.1109/ICCVW.2019.00516 |
Summary: |
Explainable Artificial Intelligence (XAI) methods are typically deployed to explain and debug black-box machine learning models. However, most proposed XAI methods are black-boxes themselves and designed for images. Thus, they rely on visual interpretability to evaluate and prove explanations. In this work, we apply XAI methods previously used in the image and text-domain on time series. We present a methodology to test and evaluate various XAI methods on time series by introducing new verification techniques to incorporate the temporal dimension. We further conduct preliminary experiments to assess the quality of selected XAI method explanations with various verification methods on a range of datasets and inspecting quality metrics on it. We demonstrate that in our initial experiments, SHAP works robust for all models, but others like DeepLIFT, LRP, and Saliency Maps work better with specific architectures.
|
Subject (DDC): | 004 Computer Science |
Keywords: | Time-Series, explainable-ai, explainable-ai-evaluation |
Link to License: | In Copyright |
Bibliography of Konstanz: | Yes |
SCHLEGEL, Udo, Hiba ARNOUT, Mennatallah EL-ASSADY, Daniela OELKE, Daniel A. KEIM, 2019. Towards A Rigorous Evaluation Of XAI Methods On Time Series. 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). Seoul, Korea (South), Oct 27, 2019 - Oct 28, 2019. In: 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). Piscataway, NJ:IEEE, pp. 4321-4325. ISSN 2473-9936. eISSN 2473-9944. ISBN 978-1-72815-023-9. Available under: doi: 10.1109/ICCVW.2019.00516
@inproceedings{Schlegel2019-10Towar-50801, title={Towards A Rigorous Evaluation Of XAI Methods On Time Series}, year={2019}, doi={10.1109/ICCVW.2019.00516}, isbn={978-1-72815-023-9}, issn={2473-9936}, address={Piscataway, NJ}, publisher={IEEE}, booktitle={2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)}, pages={4321--4325}, author={Schlegel, Udo and Arnout, Hiba and El-Assady, Mennatallah and Oelke, Daniela and Keim, Daniel A.} }
<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/rdf/resource/123456789/50801"> <dc:creator>Schlegel, Udo</dc:creator> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:creator>Keim, Daniel A.</dc:creator> <dc:contributor>El-Assady, Mennatallah</dc:contributor> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/> <dc:rights>terms-of-use</dc:rights> <dc:contributor>Arnout, Hiba</dc:contributor> <dc:contributor>Schlegel, Udo</dc:contributor> <dc:creator>El-Assady, Mennatallah</dc:creator> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/50801/1/Schlegel_2-1iaybk1cefn2y7.pdf"/> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-09-11T11:41:53Z</dcterms:available> <dcterms:issued>2019-10</dcterms:issued> <dc:contributor>Oelke, Daniela</dc:contributor> <dc:creator>Arnout, Hiba</dc:creator> <dc:language>eng</dc:language> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-09-11T11:41:53Z</dc:date> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/50801/1/Schlegel_2-1iaybk1cefn2y7.pdf"/> <dcterms:abstract xml:lang="eng">Explainable Artificial Intelligence (XAI) methods are typically deployed to explain and debug black-box machine learning models. However, most proposed XAI methods are black-boxes themselves and designed for images. Thus, they rely on visual interpretability to evaluate and prove explanations. In this work, we apply XAI methods previously used in the image and text-domain on time series. We present a methodology to test and evaluate various XAI methods on time series by introducing new verification techniques to incorporate the temporal dimension. We further conduct preliminary experiments to assess the quality of selected XAI method explanations with various verification methods on a range of datasets and inspecting quality metrics on it. We demonstrate that in our initial experiments, SHAP works robust for all models, but others like DeepLIFT, LRP, and Saliency Maps work better with specific architectures.</dcterms:abstract> <dc:creator>Oelke, Daniela</dc:creator> <dc:contributor>Keim, Daniel A.</dc:contributor> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/50801"/> <dcterms:title>Towards A Rigorous Evaluation Of XAI Methods On Time Series</dcterms:title> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> </rdf:Description> </rdf:RDF>
Schlegel_2-1iaybk1cefn2y7.pdf | 614 |