# Fractal Autoencoders for Feature Selection

arXiv: https://arxiv.org/abs/2010.09430 · HTML: https://mlsanity.com/paper/2010.09430/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [UDRN: Unified Dimensional Reduction Neural Network for Feature Selection and Feature Projection](https://mlsanity.com/paper/2207.03809/) (2022)
- [Explainable Censored Learning: Finding Critical Features with Long Term Prognostic Values for Survival Prediction](https://mlsanity.com/paper/2209.15450/) (2022)
- [Deep Feature Selection Using a Novel Complementary Feature Mask](https://mlsanity.com/paper/2209.12282/) (2022)
- [Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection](https://mlsanity.com/paper/2605.22973/) (2026)
- [Alcohol Intake Differentiates AD and LATE: A Telltale Lifestyle from Two Large-Scale Datasets](https://mlsanity.com/paper/2209.05438/) (2022)
- [Study Features via Exploring Distribution Structure](https://mlsanity.com/paper/2401.07540/) (2024)
- [Multiple-Input Auto-Encoder Guided Feature Selection for IoT Intrusion Detection Systems](https://mlsanity.com/paper/2403.15511/) (2024)
- [Unsupervised Feature Selection via Robust Autoencoder and Adaptive Graph Learning](https://mlsanity.com/paper/2512.18720/) (2025)

## Abstract (arXiv)

Feature selection reduces the dimensionality of data by identifying a subset of the most informative features. In this paper, we propose an innovative framework for unsupervised feature selection, called fractal autoencoders (FAE). It trains a neural network to pinpoint informative features for global exploring of representability and for local excavating of diversity. Architecturally, FAE extends autoencoders by adding a one-to-one scoring layer and a small sub-neural network for feature selection in an unsupervised fashion. With such a concise architecture, FAE achieves state-of-the-art performances; extensive experimental results on fourteen datasets, including very high-dimensional data, have demonstrated the superiority of FAE over existing contemporary methods for unsupervised feature selection. In particular, FAE exhibits substantial advantages on gene expression data exploration, reducing measurement cost by about 15% over the widely used L1000 landmark genes. Further, we show that the FAE framework is easily extensible with an application.