Show simple item record

dc.contributor.authorSohns, Jan‐Tobiasen_US
dc.contributor.authorGarth, Christophen_US
dc.contributor.authorLeitte, Heikeen_US
dc.contributor.editorHauser, Helwig and Alliez, Pierreen_US
dc.date.accessioned2023-03-22T15:07:11Z
dc.date.available2023-03-22T15:07:11Z
dc.date.issued2023
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14650
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14650
dc.description.abstractMachine learning algorithms are widely applied to create powerful prediction models. With increasingly complex models, humans' ability to understand the decision function (that maps from a high‐dimensional input space) is quickly exceeded. To explain a model's decisions, black‐box methods have been proposed that provide either non‐linear maps of the global topology of the decision boundary, or samples that allow approximating it locally. The former loses information about distances in input space, while the latter only provides statements about given samples, but lacks a focus on the underlying model for precise ‘What‐If'‐reasoning. In this paper, we integrate both approaches and propose an interactive exploration method using local linear maps of the decision space. We create the maps on high‐dimensional hyperplanes—2D‐slices of the high‐dimensional parameter space—based on statistical and personal feature mutability and guided by feature importance. We complement the proposed workflow with established model inspection techniques to provide orientation and guidance. We demonstrate our approach on real‐world datasets and illustrate that it allows identification of instance‐based decision boundary structures and can answer multi‐dimensional ‘What‐If'‐questions, thereby identifying counterfactual scenarios visually.en_US
dc.publisherEurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectvisual model evaluation
dc.subjectmachine learning explanation
dc.subjectinverse multi‐dimensional projection
dc.titleDecision Boundary Visualization for Counterfactual Reasoningen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersArticles
dc.description.volume42
dc.description.number1
dc.identifier.doi10.1111/cgf.14650
dc.identifier.pages7-20


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International License
Except where otherwise noted, this item's license is described as Attribution 4.0 International License