Mixing autoencoder with classifier: conceptual data visualization

TL;DR

This paper introduces a neural network model capable of producing low-dimensional topological visualizations of data, adaptable for both autoencoding and classification tasks, enabling multi-perspective data analysis.

Contribution

It presents a novel neural network that combines autoencoder and classifier functionalities to generate flexible, topologically meaningful visualizations for both structural and conceptual data insights.

Findings

Effective visualization of data topology as autoencoder

Conceptual visualization constrained by labels

Flexible multi-perspective data analysis

Abstract

In this short paper, a neural network that is able to form a low dimensional topological hidden representation is explained. The neural network can be trained as an autoencoder, a classifier or mix of both, and produces different low dimensional topological map for each of them. When it is trained as an autoencoder, the inherent topological structure of the data can be visualized, while when it is trained as a classifier, the topological structure is further constrained by the concept, for example the labels the data, hence the visualization is not only structural but also conceptual. The proposed neural network significantly differ from many dimensional reduction models, primarily in its ability to execute both supervised and unsupervised dimensional reduction. The neural network allows multi perspective visualization of the data, and thus giving more flexibility in data analysis. This paper is supported by preliminary but intuitive visualization experiments.