q-SNE: Visualizing Data using q-Gaussian Distributed Stochastic Neighbor Embedding

TL;DR

q-SNE is a novel dimensionality reduction technique that generalizes t-SNE and SNE using a q-Gaussian distribution, offering more flexible and powerful visualization of high-dimensional data in 2D or 3D.

Contribution

The paper introduces q-SNE, a new method that unifies and extends existing techniques like t-SNE and SNE through a parameterized q-Gaussian distribution for improved visualization.

Findings

q-SNE outperforms SNE, t-SNE, and UMAP in visualization quality.

q-SNE provides better classification accuracy in embedded space.

Adjusting q allows optimal visualization tailored to specific datasets.

Abstract

The dimensionality reduction has been widely introduced to use the high-dimensional data for regression, classification, feature analysis, and visualization. As the one technique of dimensionality reduction, a stochastic neighbor embedding (SNE) was introduced. The SNE leads powerful results to visualize high-dimensional data by considering the similarity between the local Gaussian distributions of high and low-dimensional space. To improve the SNE, a t-distributed stochastic neighbor embedding (t-SNE) was also introduced. To visualize high-dimensional data, the t-SNE leads to more powerful and flexible visualization on 2 or 3-dimensional mapping than the SNE by using a t-distribution as the distribution of low-dimensional data. Recently, Uniform manifold approximation and projection (UMAP) is proposed as a dimensionality reduction technique. We present a novel technique called a q-Gaussian distributed stochastic neighbor embedding (q-SNE). The q-SNE leads to more powerful and flexible visualization on 2 or 3-dimensional mapping than the t-SNE and the SNE by using a q-Gaussian distribution as the distribution of low-dimensional data. The q-Gaussian distribution includes the Gaussian distribution and the t-distribution as the special cases with q=1.0 and q=2.0. Therefore, the q-SNE can also express the t-SNE and the SNE by changing the parameter q, and this makes it possible to find the best visualization by choosing the parameter q. We show the performance of q-SNE as visualization on 2-dimensional mapping and classification by k-Nearest Neighbors (k-NN) classifier in embedded space compared with SNE, t-SNE, and UMAP by using the datasets MNIST, COIL-20, OlivettiFaces, FashionMNIST, and Glove.