# Relational Autoencoder for Feature Extraction

arXiv: https://arxiv.org/abs/1802.03145 · HTML: https://mlsanity.com/paper/1802.03145/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2018.

## Built on by (most cited first, 23 of 23)

- [SwitchTab: Switched Autoencoders Are Effective Tabular Learners](https://mlsanity.com/paper/2401.02013/) (2024)
- [Graph-level Representation Learning with Joint-Embedding Predictive Architectures](https://mlsanity.com/paper/2309.16014/) (2023)
- [Deep Graph Convolutional Reinforcement Learning for Financial Portfolio Management -- DeepPocket](https://mlsanity.com/paper/2105.08664/) (2021)
- [SeriesGAN: Time Series Generation via Adversarial and Autoregressive Learning](https://mlsanity.com/paper/2410.21203/) (2024)
- [Symbolic Regression as Feature Engineering Method for Machine and Deep Learning Regression Tasks](https://mlsanity.com/paper/2311.06028/) (2023)
- [Sensitivity Decouple Learning for Image Compression Artifacts Reduction](https://mlsanity.com/paper/2405.09291/) (2024)
- [Unveiling Multiple Descents in Unsupervised Autoencoders](https://mlsanity.com/paper/2406.11703/) (2024)
- [Sparse L1-Autoencoders for Scientific Data Compression](https://mlsanity.com/paper/2405.14270/) (2024)
- [LioNets: A Neural-Specific Local Interpretation Technique Exploiting Penultimate Layer Information](https://mlsanity.com/paper/2104.06057/) (2021)
- [Causal Autoencoder-like Generation of Feedback Fuzzy Cognitive Maps with an LLM Agent](https://mlsanity.com/paper/2509.25593/) (2025)
- [Robust Anomaly Detection for Time-series Data](https://mlsanity.com/paper/2202.02721/) (2022)
- [Aligning Latent Spaces with Flow Priors](https://mlsanity.com/paper/2506.05240/) (2025)
- [Data-driven modeling of time-domain induced polarization](https://mlsanity.com/paper/2107.14796/) (2021)
- [Man versus Machine: AutoML and Human Experts' Role in Phishing Detection](https://mlsanity.com/paper/2108.12193/) (2021)
- [Texture Aware Autoencoder Pre-training And Pairwise Learning Refinement For Improved Iris Recognition](https://mlsanity.com/paper/2202.07499/) (2022)
- [Redundancy in Deep Linear Neural Networks](https://mlsanity.com/paper/2206.04490/) (2022)
- [A Review of Deep Learning Techniques for Protein Function Prediction](https://mlsanity.com/paper/2211.09705/) (2022)
- [Fake detection in imbalance dataset by Semi-supervised learning with GAN](https://mlsanity.com/paper/2212.01071/) (2022)
- [Using Autoencoders and AutoDiff to Reconstruct Missing Variables in a Set of Time Series](https://mlsanity.com/paper/2308.10496/) (2023)
- [Towards Financially Inclusive Credit Products Through Financial Time Series Clustering](https://mlsanity.com/paper/2402.11066/) (2024)
- [HistoSPACE: Histology-Inspired Spatial Transcriptome Prediction And Characterization Engine](https://mlsanity.com/paper/2408.03592/) (2024)
- [Analogue Forecast System for Daily Precipitation Prediction Using Autoencoder Feature Extraction: Application in Hong Kong](https://mlsanity.com/paper/2501.02814/) (2025)
- [Deep Learning Based Approach to Enhanced Recognition of Emotions and Behavioral Patterns of Autistic Children](https://mlsanity.com/paper/2510.07320/) (2025)

## Abstract (arXiv)

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.