Bitte benutzen Sie diese Kennung, um auf die Ressource zu verweisen: http://dx.doi.org/10.25673/81377
Titel: Active feature acquisition on data streams under feature drift
Autor(en): Beyer, Christian
Büttner, Maik
Unnikrishnan, Vishnu
Schleicher, Miro
Ntoutsi, Eirini
Spiliopoulou, MyraIn der Gemeinsamen Normdatei der DNB nachschlagen
Erscheinungsdatum: 2020
Art: Artikel
Sprache: Englisch
URN: urn:nbn:de:gbv:ma9:1-1981185920-833322
Schlagwörter: Active feature acquisition
Data streams
Feature drift
Zusammenfassung: Traditional active learning tries to identify instances for which the acquisition of the label increases model performance under budget constraints. Less research has been devoted to the task of actively acquiring feature values, whereupon both the instance and the feature must be selected intelligently and even less to a scenario where the instances arrive in a stream with feature drift.We propose an active feature acquisition strategy for data streams with feature drift, as well as an active feature acquisition evaluation framework. We also implement a baseline that chooses features randomly and compare the random approach against eight different methods in a scenario where we can acquire at most one feature at the time per instance and where all features are considered to cost the same. Our initial experiments on 9 different data sets, with 7 different degrees of missing features and 8 different budgets show that our developed methods outperform the random acquisition on 7 data sets and have a comparable performance on the remaining two.
URI: https://opendata.uni-halle.de//handle/1981185920/83332
http://dx.doi.org/10.25673/81377
Open-Access: Open-Access-Publikation
Nutzungslizenz: (CC BY 4.0) Creative Commons Namensnennung 4.0 International(CC BY 4.0) Creative Commons Namensnennung 4.0 International
Sponsor/Geldgeber: Projekt DEAL 2020
Journal Titel: Annals of telecommunications
Verlag: Lavoisier
Verlagsort: Paris
Band: 75
Heft: 9/10
Originalveröffentlichung: 10.1007/s12243-020-00775-2
Seitenanfang: 597
Seitenende: 611
Enthalten in den Sammlungen:Fakultät für Informatik (OA)

Dateien zu dieser Ressource:
Datei Beschreibung GrößeFormat 
Beyer et al._Active feature_2020.pdfZweitveröffentlichung717.73 kBAdobe PDFMiniaturbild
Öffnen/Anzeigen