Latent Space Exploration Using Generative Kernel PCA

TL;DR

This paper explores how generative kernel PCA can be used to interpret and navigate the latent spaces of datasets, enabling the generation of new data points and understanding of data novelty.

Contribution

It introduces a method for using generative kernel PCA to explore and interpret latent spaces, including applications to ECG signals and novelty detection.

Findings

Latent space exploration enables interpretation of dataset components.

Generated points can be used to understand data structure.

The method aids in identifying and explaining novel data points.

Abstract

Kernel PCA is a powerful feature extractor which recently has seen a reformulation in the context of Restricted Kernel Machines (RKMs). These RKMs allow for a representation of kernel PCA in terms of hidden and visible units similar to Restricted Boltzmann Machines. This connection has led to insights on how to use kernel PCA in a generative procedure, called generative kernel PCA. In this paper, the use of generative kernel PCA for exploring latent spaces of datasets is investigated. New points can be generated by gradually moving in the latent space, which allows for an interpretation of the components. Firstly, examples of this feature space exploration on three datasets are shown with one of them leading to an interpretable representation of ECG signals. Afterwards, the use of the tool in combination with novelty detection is shown, where the latent space around novel patterns in the data is explored. This helps in the interpretation of why certain points are considered as novel.