VERA: Generating Visual Explanations of Two-Dimensional Embeddings via Region Annotation

TL;DR

VERA is a method that automatically generates static, region-based visual explanations for two-dimensional embeddings, helping users interpret complex data structures efficiently.

Contribution

It introduces a general-purpose approach for explaining embeddings through automatic, concise visual annotations linked to human-interpretable features.

Findings

VERA effectively summarizes embedding structures with concise visual explanations.

User study shows VERA reduces time and effort compared to interactive tools.

VERA aids in understanding high-dimensional data visualizations.

Abstract

Two-dimensional embeddings obtained from dimensionality reduction techniques such as MDS, t-SNE, or UMAP, are widely used to visualize high-dimensional data and support researchers in visually identifying clusters, outliers, and other interesting patterns in the data. However, the main challenge is not only to detect such patterns, but to explain what they represent in terms of the original, human-interpretable features of the data. Existing approaches often rely on interactive exploration or direct feature encodings, requiring substantial manual inspection that can be time-consuming and repetitive. As an alternative, we propose VERA (Visual Explanations via Region Annotation), a general-purpose method for explaining two-dimensional embeddings through automatically generated, static, region-based visual explanations. VERA identifies informative regions in the embedding space and associates them with user-provided human-interpretable features, producing concise visual annotations that summarize the structure of the embedding landscape at a glance. Rather than merely showing where feature values occur, VERA automatically filters, merges, and ranks candidate explanations, enabling users to focus on the most informative embedding structures without manual exploration. We demonstrate VERA's utility on several real-world datasets and evaluate its effectiveness in a user study comparing it with the utility of a comprehensive interactive data mining toolkit. Our results show that VERA's generated static explanations can convey the essential insights of complex embeddings and support users in typical exploratory data analysis tasks, while requiring significantly less time and user effort.