Journal
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
Volume 28, Issue 1, Pages 529-539Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TVCG.2021.3114694
Keywords
Visualization; Task analysis; Principal component analysis; Measurement; Manifolds; Linearity; Visual perception; Dimensionality reduction; visual cluster analysis; perception-based evaluation
Categories
Funding
- National Natural Science Foundation of China [61872389]
Ask authors/readers for more resources
This study investigates the influence of different dimensionality reduction techniques on visual cluster analysis, focusing on linearity and locality properties. Four controlled experiments were conducted to evaluate the performance of 12 representative techniques in cluster identification, membership identification, distance comparison, and density comparison tasks. The study also assessed users' subjective preference regarding the quality of projected clusters.
Dimensionality Reduction (DR) techniques can generate 2D projections and enable visual exploration of cluster structures of high-dimensional datasets. However, different DR techniques would yield various patterns, which significantly affect the performance of visual cluster analysis tasks. We present the results of a user study that investigates the influence of different DR techniques on visual cluster analysis. Our study focuses on the most concerned property types, namely the linearity and locality, and evaluates twelve representative DR techniques that cover the concerned properties. Four controlled experiments were conducted to evaluate how the DR techniques facilitate the tasks of 1) cluster identification, 2) membership identification, 3) distance comparison, and 4) density comparison, respectively. We also evaluated users' subjective preference of the DR techniques regarding the quality of projected clusters. The results show that: 1) Non-linear and Local techniques are preferred in cluster identification and membership identification; 2) Linear techniques perform better than non-linear techniques in density comparison; 3) UMAP (Uniform Manifold Approximation and Projection) and t-SNE (t-Distributed Stochastic Neighbor Embedding) perform the best in cluster identification and membership identification; 4) NMF (Nonnegative Matrix Factorization) has competitive performance in distance comparison; 5) t-SNLE (t-Distributed Stochastic Neighbor Linear Embedding) has competitive performance in density comparison.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available