How to boost autoencoders?

TL;DR

This paper explores boosting techniques for autoencoders, addressing challenges and proposing a framework to enhance their performance in anomaly detection and clustering tasks.

Contribution

It introduces a novel boosting framework tailored for autoencoders, overcoming existing challenges and improving their effectiveness in key applications.

Findings

Boosted autoencoders improve anomaly detection accuracy.

The framework enhances clustering performance with autoencoders.

Experimental results demonstrate the effectiveness of the proposed method.

Abstract

Autoencoders are a category of neural networks with applications in numerous domains and hence, improvement of their performance is gaining substantial interest from the machine learning community. Ensemble methods, such as boosting, are often adopted to enhance the performance of regular neural networks. In this work, we discuss the challenges associated with boosting autoencoders and propose a framework to overcome them. The proposed method ensures that the advantages of boosting are realized when either output (encoded or reconstructed) is used. The usefulness of the boosted ensemble is demonstrated in two applications that widely employ autoencoders: anomaly detection and clustering.