Work

Interpretable visualizations of data spaces for classification problems

Year: 2026

Type: article

Abstract: How do classification models ‘see’ our data? Based on their success in delineating behaviors, there must be some lens through which it is easy to see the boundary between classes; however, our current set of visualization techniques makes this prospect difficult. In this work, we propose a hybrid supervised-unsupervised technique distinctly suited to visualizing the decision boundaries determined by classification problems. This method provides a human-interpretable map that can be analyzed qualitatively and quantitatively, which we demonstrate through several established examples from literature. While we discuss this method in the context of chemistry-driven problems, its application can be generalized across subfields for ‘unboxing’ the operations of machine-learning classification models.

Source: Machine Learning Science and Technology

DOI: 10.1088/2632-2153/ae466e

Authors: Christian Jorgensen, Arthur Y Lin, Rhushil Vasavada, Rose K Cersonsky

Institution: University of Wisconsin–Madison

Language: English

Topic: Data Visualization and Analytics

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $3,000

Funder: Wisconsin Alumni Research Foundation