DeforestVis: Behaviour Analysis of Machine Learning Models with Surrogate Decision Stumps

Simple item page
dc.contributor.authorChatzimparmpas, Angelosen_US
dc.contributor.authorMartins, Rafeal M.en_US
dc.contributor.authorTelea, Alexandru C.en_US
dc.contributor.authorKerren, Andreasen_US
dc.contributor.editorAlliez, Pierreen_US
dc.contributor.editorWimmer, Michaelen_US
dc.date.accessioned2024-12-19T11:14:50Z
dc.date.available2024-12-19T11:14:50Z
dc.date.issued2024
dc.description.abstractAs the complexity of machine learning (ML) models increases and their application in different (and critical) domains grows, there is a strong demand for more interpretable and trustworthy ML. A direct, model‐agnostic, way to interpret such models is to train surrogate models—such as rule sets and decision trees—that sufficiently approximate the original ones while being simpler and easier‐to‐explain. Yet, rule sets can become very lengthy, with many if–else statements, and decision tree depth grows rapidly when accurately emulating complex ML models. In such cases, both approaches can fail to meet their core goal—providing users with model interpretability. To tackle this, we propose DeforestVis, a visual analytics tool that offers summarization of the behaviour of complex ML models by providing surrogate decision stumps (one‐level decision trees) generated with the Adaptive Boosting (AdaBoost) technique. DeforestVis helps users to explore the complexity versus fidelity trade‐off by incrementally generating more stumps, creating attribute‐based explanations with weighted stumps to justify decision making, and analysing the impact of rule overriding on training instance allocation between one or more stumps. An independent test set allows users to monitor the effectiveness of manual rule changes and form hypotheses based on case‐by‐case analyses. We show the applicability and usefulness of DeforestVis with two use cases and expert interviews with data analysts and model developers.en_US
dc.description.number6
dc.description.sectionheadersORIGINAL ARTICLES
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15004
dc.identifier.pages19 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15004
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15004
dc.publisher© 2024 Eurographics ‐ 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.subjectsurrogate model
dc.subjectmodel understanding
dc.subjectadaptive boosting
dc.subjectmachine learning
dc.subjectvisual analytics
dc.subjectvisualization
dc.titleDeforestVis: Behaviour Analysis of Machine Learning Models with Surrogate Decision Stumpsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
02_cgf15004.pdf
Size:
2.48 MB
Format:
Adobe Portable Document Format
Download
Collections
43-Issue 6