Publikation: A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI
Dateien
Datum
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
DOI (zitierfähiger Link)
Internationale Patentnummer
Link zur Lizenz
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
Explainable Artificial Intelligence (XAI) has gained significant attention recently as the demand for transparency and interpretability of machine learning models has increased. In particular, XAI for time series data has become increasingly important in finance, healthcare, and climate science. However, evaluating the quality of explanations, such as attributions provided by XAI techniques, remains challenging. This paper provides an in-depth analysis of using perturbations to evaluate attributions extracted from time series models. A perturbation analysis involves systematically modifying the input data and evaluating the impact on the attributions generated by the XAI method. We apply this approach to several state-of-the-art XAI techniques and evaluate their performance on three time series classification datasets. Our results demonstrate that the perturbation analysis approach can effectively evaluate the quality of attributions and provide insights into the strengths and limitations of XAI techniques. Such an approach can guide the selection of XAI methods for time series data, e.g., focusing on return time rather than precision, and facilitate the development of more reliable and interpretable machine learning models for time series analysis.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
SCHLEGEL, Udo, Daniel A. KEIM, 2023. A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI. 1st World Conference on Explainable Artificial Intelligence (xAI 2023). Lisbon, Portugal, 26. Juli 2023 - 28. Juli 2023. In: LONGO, Luca, Hrsg.. Explainable Artificial Intelligence : First World Conference, xAI 2023, Proceedings. Cham: Springer, 2023, S. 165-180. Communications in Computer and Information Science (CCIS). 1902. ISBN 978-3-031-44069-4. Verfügbar unter: doi: 10.1007/978-3-031-44070-0_9BibTex
@inproceedings{Schlegel2023intoP-70354, year={2023}, doi={10.1007/978-3-031-44070-0_9}, title={A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI}, number={1902}, isbn={978-3-031-44069-4}, publisher={Springer}, address={Cham}, series={Communications in Computer and Information Science (CCIS)}, booktitle={Explainable Artificial Intelligence : First World Conference, xAI 2023, Proceedings}, pages={165--180}, editor={Longo, Luca}, 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/123456789/70354"> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-07-09T09:02:18Z</dc:date> <dc:contributor>Keim, Daniel A.</dc:contributor> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/70354"/> <dc:contributor>Schlegel, Udo</dc:contributor> <dc:creator>Keim, Daniel A.</dc:creator> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/70354/1/Schlegel_2-1l2z71qk6ds6j4.pdf"/> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/70354/1/Schlegel_2-1l2z71qk6ds6j4.pdf"/> <dcterms:issued>2023</dcterms:issued> <dc:creator>Schlegel, Udo</dc:creator> <dcterms:title>A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI</dcterms:title> <dcterms:abstract>Explainable Artificial Intelligence (XAI) has gained significant attention recently as the demand for transparency and interpretability of machine learning models has increased. In particular, XAI for time series data has become increasingly important in finance, healthcare, and climate science. However, evaluating the quality of explanations, such as attributions provided by XAI techniques, remains challenging. This paper provides an in-depth analysis of using perturbations to evaluate attributions extracted from time series models. A perturbation analysis involves systematically modifying the input data and evaluating the impact on the attributions generated by the XAI method. We apply this approach to several state-of-the-art XAI techniques and evaluate their performance on three time series classification datasets. Our results demonstrate that the perturbation analysis approach can effectively evaluate the quality of attributions and provide insights into the strengths and limitations of XAI techniques. Such an approach can guide the selection of XAI methods for time series data, e.g., focusing on return time rather than precision, and facilitate the development of more reliable and interpretable machine learning models for time series analysis.</dcterms:abstract> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-07-09T09:02:18Z</dcterms:available> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dc:language>eng</dc:language> </rdf:Description> </rdf:RDF>