Not logged in.

Contribution Details

Type Conference or Workshop Paper
Scope Discipline-based scholarship
Published in Proceedings Yes
Title Interactive Visual Explanation of Incremental Data Labeling
Organization Unit
Authors
  • Raphael Beckmann
  • Cristian Blaga
  • Mennatallah El-Assady
  • Matthias Zeppelzauer
  • Jürgen Bernard
Editors
  • Jürgen Bernard
  • Marco Angelini
Presentation Type paper
Item Subtype Original Work
Refereed Yes
Status Published in final form
Language
  • English
Event Title EuroVis Workshop on Visual Analytics (EuroVA)
Event Type workshop
Event Location Rome, Italy
Event Start Date June 13 - 2022
Event End Date June 17 - 2022
Publisher Eurographics Association
Abstract Text We present a visual analytics approach for the in-depth analysis and explanation of incremental machine learning processes that are based on data labeling. Our approach offers multiple perspectives to explain the process, i.e., data characteristics, label distribution, class characteristics, and classifier characteristics. Additionally, we introduce metrics from which we derive novel aggregated analytic views that enable the analysis of the process over time. We demonstrate the capabilities of our approach in a case study and thereby demonstrate how our approach improves the transparency of the iterative learning process.
Digital Object Identifier 10.2312/eurova.20221073
Other Identification Number merlin-id:23096
PDF File Download from ZORA
Export BibTeX
EP3 XML (ZORA)