# Spectral Clustering via Ensemble Deep Autoencoder Learning (SC-EDAE)

arXiv: https://arxiv.org/abs/1901.02291 · HTML: https://mlsanity.com/paper/1901.02291/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jan 2019.

## Built on by (most cited first, 10 of 10)

- [Deep Clustering: A Comprehensive Survey](https://mlsanity.com/paper/2210.04142/) (2022)
- [Attention-driven Graph Clustering Network](https://mlsanity.com/paper/2108.05499/) (2021)
- [Deep Clustering Using the Soft Silhouette Score: Towards Compact and Well-Separated Clusters](https://mlsanity.com/paper/2402.00608/) (2024)
- [Bootstrap Deep Spectral Clustering with Optimal Transport](https://mlsanity.com/paper/2508.04200/) (2025)
- [Delving into Spectral Clustering with Vision-Language Representations](https://mlsanity.com/paper/2602.09586/) (2026)
- [Random projection tree similarity metric for SpectralNet](https://mlsanity.com/paper/2302.13168/) (2023)
- [Snapshot Spectral Clustering -- a costless approach to deep clustering ensembles generation](https://mlsanity.com/paper/2307.08591/) (2023)
- [Transferable Deep Clustering Model](https://mlsanity.com/paper/2310.04946/) (2023)
- [Deep Clustering via Distribution Learning](https://mlsanity.com/paper/2408.03407/) (2024)
- [Scalable Deep Subspace Clustering Network](https://mlsanity.com/paper/2512.21434/) (2025)

## Abstract (arXiv)

Recently, a number of works have studied clustering strategies that combine classical clustering algorithms and deep learning methods. These approaches follow either a sequential way, where a deep representation is learned using a deep autoencoder before obtaining clusters with k-means, or a simultaneous way, where deep representation and clusters are learned jointly by optimizing a single objective function. Both strategies improve clustering performance, however the robustness of these approaches is impeded by several deep autoencoder setting issues, among which the weights initialization, the width and number of layers or the number of epochs. To alleviate the impact of such hyperparameters setting on the clustering performance, we propose a new model which combines the spectral clustering and deep autoencoder strengths in an ensemble learning framework. Extensive experiments on various benchmark datasets demonstrate the potential and robustness of our approach compared to state-of-the-art deep clustering methods.