Classes are Not Clusters: Improving Label-Based Evaluation of Dimensionality Reduction

A common way to evaluate the reliability of dimensionality reduction (DR) embeddings is to quantify how well labeled classes form compact, mutually separated clusters in the embeddings. This approach is based on the assumption that the classes stay as clear clusters in the original high-dimensional...

Celý popis

Podrobná bibliografie

Vydáno v:	IEEE transactions on visualization and computer graphics Ročník 30; číslo 1; s. 781 - 791
Hlavní autoři:	Jeon, Hyeon, Kuo, Yun-Hsin, Aupetit, Michael, Ma, Kwan-Liu, Seo, Jinwook
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	IEEE 01.01.2024
Témata:	Clustering Clustering Validation Measures Degradation Dimensionality reduction Dimensionality Reduction Evaluation Distortion measurement Extraterrestrial measurements Nonlinear distortion Reliability Scalability
ISSN:	1077-2626, 1941-0506, 1941-0506
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!