Visualizing Pairwise Feature Interactions in Neural Additive Models

Simple item page
dc.contributor.authorSteinparz, Christianen_US
dc.contributor.authorHinterreiter, Andreasen_US
dc.contributor.authorStreit, Marcen_US
dc.contributor.editorGillmann, Christinaen_US
dc.contributor.editorKrone, Michaelen_US
dc.contributor.editorLenti, Simoneen_US
dc.date.accessioned2023-06-10T06:31:46Z
dc.date.available2023-06-10T06:31:46Z
dc.date.issued2023
dc.description.abstractWe present an approach for incorporating feature interactions into Neural Additive Models (NAMs), building upon existing work in this area, to enhance their predictive capabilities while maintaining interpretability. Our contribution focuses on the visual exploration and management of the increased number of feature maps resulting from the addition of pairwise feature combinations to NAMs. This method allows for effectively visualizing individual and pairwise feature interactions using line plots and heatmaps, respectively. To address the potential explosion in the number of feature maps, we apply different scoring functions to compute the importance of a feature map and then filter and sort them based on their importance. The proposed interactive dashboard effectively manages large sets of feature maps, while preserving the white-box properties of NAMs.en_US
dc.description.seriesinformationEuroVis 2023 - Posters
dc.identifier.doi10.2312/evp.20231077
dc.identifier.isbn978-3-03868-220-2
dc.identifier.pages97-99
dc.identifier.pages3 pages
dc.identifier.urihttps://doi.org/10.2312/evp.20231077
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/evp20231077
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies -> Neural networks; Human-centered computing -> Visual analytics
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.subjectHuman centered computing
dc.subjectVisual analytics
dc.titleVisualizing Pairwise Feature Interactions in Neural Additive Modelsen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
097-099.pdf
Size:
596.81 KB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
5545-file-i7.pdf
Size:
2 MB
Format:
Adobe Portable Document Format
Download
Collections
EuroVisPosters2023