Relational Autoencoder for Feature Extraction

TL;DR

This paper introduces a relational autoencoder that incorporates data sample relationships into feature extraction, leading to more robust features and improved classification performance over traditional autoencoders.

Contribution

It proposes a novel relational autoencoder model that considers data relationships, extending existing autoencoders and demonstrating improved feature robustness.

Findings

Relational autoencoder achieves lower reconstruction loss.

Generated features lead to lower classification error.

Model outperforms traditional autoencoders on benchmark datasets.

Abstract

Feature extraction becomes increasingly important as data grows high dimensional. Autoencoder as a neural network based feature extraction method achieves great success in generating abstract features of high dimensional data. However, it fails to consider the relationships of data samples which may affect experimental results of using original and new features. In this paper, we propose a Relation Autoencoder model considering both data features and their relationships. We also extend it to work with other major autoencoder models including Sparse Autoencoder, Denoising Autoencoder and Variational Autoencoder. The proposed relational autoencoder models are evaluated on a set of benchmark datasets and the experimental results show that considering data relationships can generate more robust features which achieve lower construction loss and then lower error rate in further classification compared to the other variants of autoencoders.