Interactive Visual Explanation of Incremental Data Labeling

Abstract
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.
Description

        
@inproceedings{
10.2312:eurova.20221073
, booktitle = {
EuroVis Workshop on Visual Analytics (EuroVA)
}, editor = {
Bernard, Jürgen
and
Angelini, Marco
}, title = {{
Interactive Visual Explanation of Incremental Data Labeling
}}, author = {
Beckmann, Raphael
and
Blaga, Cristian
and
El-Assady, Mennatallah
and
Zeppelzauer, Matthias
and
Bernard, Jürgen
}, year = {
2022
}, publisher = {
The Eurographics Association
}, ISSN = {
2664-4487
}, ISBN = {
978-3-03868-183-0
}, DOI = {
10.2312/eurova.20221073
} }
Citation
Collections