MIK: Modified Isolation Kernel for Biological Sequence Visualization, Classification, and Clustering

TL;DR

This paper introduces the Modified Isolation Kernel (MIK), a new density-based similarity measure for t-SNE that improves local and global structure preservation in high-dimensional data visualization.

Contribution

It proposes MIK, an adaptive, robust kernel that enhances t-SNE's ability to capture local structures compared to traditional Gaussian kernels.

Findings

MIK outperforms Gaussian and isolation kernels in structure preservation.

Improved visualization of clusters and subclusters.

Enhanced computational efficiency with MIK.

Abstract

The t-Distributed Stochastic Neighbor Embedding (t-SNE) has emerged as a popular dimensionality reduction technique for visualizing high-dimensional data. It computes pairwise similarities between data points by default using an RBF kernel and random initialization (in low-dimensional space), which successfully captures the overall structure but may struggle to preserve the local structure efficiently. This research proposes a novel approach called the Modified Isolation Kernel (MIK) as an alternative to the Gaussian kernel, which is built upon the concept of the Isolation Kernel. MIK uses adaptive density estimation to capture local structures more accurately and integrates robustness measures. It also assigns higher similarity values to nearby points and lower values to distant points. Comparative research using the normal Gaussian kernel, the isolation kernel, and several initialization techniques, including random, PCA, and random walk initializations, are used to assess the proposed approach (MIK). Additionally, we compare the computational efficiency of all $3$ kernels with $3$ different initialization methods. Our experimental results demonstrate several advantages of the proposed kernel (MIK) and initialization method selection. It exhibits improved preservation of the local and global structure and enables better visualization of clusters and subclusters in the embedded space. These findings contribute to advancing dimensionality reduction techniques and provide researchers and practitioners with an effective tool for data exploration, visualization, and analysis in various domains.