AI RESEARCH
VERA: Generating Visual Explanations of Two-Dimensional Embeddings via Region Annotation
arXiv CS.LG
•
ArXi:2406.04808v2 Announce Type: replace Two-dimensional embeddings obtained from dimensionality reduction techniques such as MDS, t-SNE, or UMAP, are widely used to visualize high-dimensional data and 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.