181 citations · 310 across the 26 of their papers we have counts for
7 papers · 1 filter
Metric Design != Metric Behavior: Improving Metric Selection for the Unbiased Evaluation of Dimensionality Reduction
Jiyeon Bae, Hyeon Jeon, Jinwook Seo
Evaluating the accuracy of dimensionality reduction (DR) projections in preserving the structure of high-dimensional data is crucial for reliable visual analytics. Diverse evaluati…
Measuring the Validity of Clustering Validation Datasets
Hyeon Jeon, Michaël Aupetit, DongHwa Shin +3
Clustering techniques are often validated using benchmark datasets where class labels are used as ground-truth clusters. However, depending on the datasets, class labels may not al…
ZADU: A Python Library for Evaluating the Reliability of Dimensionality Reduction Embeddings
Hyeon Jeon, Aeri Cho, Jinhwa Jang +5
Dimensionality reduction (DR) techniques inherently distort the original structure of input high-dimensional data, producing imperfect low-dimensional embeddings. Diverse distortio…
Classes are not Clusters: Improving Label-based Evaluation of Dimensionality Reduction
Hyeon Jeon, Yun-Hsin Kuo, Michaël Aupetit +2
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 embedd…
Sanity Check for External Clustering Validation Benchmarks using Internal Validation Measures
Hyeon Jeon, Michael Aupetit, DongHwa Shin +3
We address the lack of reliability in benchmarking clustering techniques based on labeled datasets. A standard scheme in external clustering validation is to use class labels as gr…
Uniform Manifold Approximation with Two-phase Optimization
Hyeon Jeon, Hyung-Kwon Ko, Soohyun Lee +2
We introduce Uniform Manifold Approximation with Two-phase Optimization (UMATO), a dimensionality reduction (DR) technique that improves UMAP to capture the global structure of hig…
Measuring and Explaining the Inter-Cluster Reliability of Multidimensional Projections
Hyeon Jeon, Hyung-Kwon Ko, Jaemin Jo +2
We propose Steadiness and Cohesiveness, two novel metrics to measure the inter-cluster reliability of multidimensional projection (MDP), specifically how well the inter-cluster str…