# Denoising Adversarial Autoencoders

## TL;DR

This paper introduces denoising adversarial autoencoders that combine denoising and adversarial regularisation to produce more robust representations and improve sample quality in unsupervised learning.

## Contribution

It proposes a novel method that integrates denoising with adversarial autoencoders, along with a new analysis of their training and sampling processes.

## Key findings

- Denoising autoencoders improve classification performance.
- Samples generated are more consistent with input data.
- Denoising enhances the quality of learned representations.

## Abstract

Unsupervised learning is of growing interest because it unlocks the potential held in vast amounts of unlabelled data to learn useful representations for inference. Autoencoders, a form of generative model, may be trained by learning to reconstruct unlabelled input data from a latent representation space. More robust representations may be produced by an autoencoder if it learns to recover clean input samples from corrupted ones. Representations may be further improved by introducing regularisation during training to shape the distribution of the encoded data in latent space. We suggest denoising adversarial autoencoders, which combine denoising and regularisation, shaping the distribution of latent space using adversarial training. We introduce a novel analysis that shows how denoising may be incorporated into the training and sampling of adversarial autoencoders. Experiments are performed to assess the contributions that denoising makes to the learning of representations for classification and sample synthesis. Our results suggest that autoencoders trained using a denoising criterion achieve higher classification performance, and can synthesise samples that are more consistent with the input data than those trained without a corruption process.