Revisiting Dimensionality Reduction Techniques for Visual Cluster Analysis: An Empirical Study

Different dimensionality reduction results of the ExtYaleB dataset, which contains 320 images of five people. The twelve dimensionality reduction techniques fall into four categories: Non-linear & Local (NL&Lc), Non-linear & Global (NL&G), Linear & Local (L&Lc), and Linear & Global (L&G). Instances of task stimuli: (a) Cluster identification (T1), (b) Membership identification (T2), (c) Distance comparison (T3), and (d) Density comparison (T4). (e) lasso tool used in T1-T4.

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.