Enhanced Attribute-Based Explanations of Multidimensional Projections

Simple item page
dc.contributor.authorDriel, Daan vanen_US
dc.contributor.authorZhai, Xiaoruien_US
dc.contributor.authorTian, Zonglinen_US
dc.contributor.authorTelea, Alexandruen_US
dc.contributor.editorTurkay, Cagatay and Vrotsou, Katerinaen_US
dc.date.accessioned2020-05-24T13:31:30Z
dc.date.available2020-05-24T13:31:30Z
dc.date.issued2020
dc.description.abstractMultidimensional projections (MPs) are established tools for exploring the structure of high-dimensional datasets to reveal groups of similar observations. For optimal usage, MPs can be augmented with mechanisms that explain what such points have in common that makes them similar. We extend the set of such explanatory instruments by two new techniques. First, we compute and encode the local dimensionality of the data in the projection, thereby showing areas where the MP can be well explained by a few latent variables. Secondly, we compute and display local attribute correlations, thereby helping the user to discover alternative explanations for the underlying phenomenon. We implement our explanatory tools using an image-based approach, which is efficient to compute, scales well visually for large and dense MP scatterplots, and can handle any projection technique. We demonstrate our approach using several datasets.en_US
dc.description.sectionheadersVisual Analysis of High Dimensional and Temporal Data
dc.description.seriesinformationEuroVis Workshop on Visual Analytics (EuroVA)
dc.identifier.doi10.2312/eurova.20201084
dc.identifier.isbn978-3-03868-116-8
dc.identifier.issn2664-4487
dc.identifier.pages37-41
dc.identifier.urihttps://doi.org/10.2312/eurova.20201084
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/eurova20201084
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/]
dc.subjectHuman centered computing
dc.subjectVisualization design and evaluation methods
dc.titleEnhanced Attribute-Based Explanations of Multidimensional Projectionsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
037-041.pdf
Size:
2.81 MB
Format:
Adobe Portable Document Format
Download
Collections
EuroVA2020