# An analysis on the use of autoencoders for representation learning: fundamentals, learning task case studies, explainability and challenges

arXiv: https://arxiv.org/abs/2005.10516 · HTML: https://mlsanity.com/paper/2005.10516/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2020.

## Built on by (most cited first, 12 of 12)

- [DoE2Vec: Deep-learning Based Features for Exploratory Landscape Analysis](https://mlsanity.com/paper/2304.01219/) (2023)
- [Exploiting auto-encoders and segmentation methods for middle-level explanations of image classification systems](https://mlsanity.com/paper/2106.05037/) (2021)
- [Reducing Data Complexity using Autoencoders with Class-informed Loss Functions](https://mlsanity.com/paper/2111.06142/) (2021)
- [Text as a Universal Interface for Transferable Personalization](https://mlsanity.com/paper/2601.04963/) (2026)
- [Representing Camera Response Function by a Single Latent Variable and Fully Connected Neural Network](https://mlsanity.com/paper/2209.03624/) (2022)
- [Trading through Earnings Seasons using Self-Supervised Contrastive Representation Learning](https://mlsanity.com/paper/2409.17392/) (2024)
- [EVolutionary Independent DEtermiNistiC Explanation](https://mlsanity.com/paper/2501.16357/) (2025)
- [GPO-VAE: Modeling Explainable Gene Perturbation Responses utilizing GRN-Aligned Parameter Optimization](https://mlsanity.com/paper/2501.18973/) (2025)
- [MUPAX: Multidimensional Problem Agnostic eXplainable AI](https://mlsanity.com/paper/2507.13090/) (2025)
- [Repeating versus Nonrepeating Fast Radio Bursts: A Deep Learning Approach to Morphological Characterization](https://mlsanity.com/paper/2509.06208/) (2025)
- [Benchmark-Ready 3D Anatomical Shape Classification](https://mlsanity.com/paper/2511.01613/) (2025)
- [Recursive Threshold Median Filter and Autoencoder for Salt-and-Pepper Denoising: SSIM analysis of Images and Entropy Maps](https://mlsanity.com/paper/2511.12212/) (2025)

## Abstract (arXiv)

In many machine learning tasks, learning a good representation of the data can be the key to building a well-performant solution. This is because most learning algorithms operate with the features in order to find models for the data. For instance, classification performance can improve if the data is mapped to a space where classes are easily separated, and regression can be facilitated by finding a manifold of data in the feature space. As a general rule, features are transformed by means of statistical methods such as principal component analysis, or manifold learning techniques such as Isomap or locally linear embedding. From a plethora of representation learning methods, one of the most versatile tools is the autoencoder. In this paper we aim to demonstrate how to influence its learned representations to achieve the desired learning behavior. To this end, we present a series of learning tasks: data embedding for visualization, image denoising, semantic hashing, detection of abnormal behaviors and instance generation. We model them from the representation learning perspective, following the state of the art methodologies in each field. A solution is proposed for each task employing autoencoders as the only learning method. The theoretical developments are put into practice using a selection of datasets for the different problems and implementing each solution, followed by a discussion of the results in each case study and a brief explanation of other six learning applications. We also explore the current challenges and approaches to explainability in the context of autoencoders. All of this helps conclude that, thanks to alterations in their structure as well as their objective function, autoencoders may be the core of a possible solution to many problems which can be modeled as a transformation of the feature space.