# Scalable Deep Subspace Clustering Network

arXiv: https://arxiv.org/abs/2512.21434 · HTML: https://mlsanity.com/paper/2512.21434/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 24 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [Deep Subspace Clustering Networks](https://mlsanity.com/paper/1709.02508/) (2017)
- [Large-scale Multi-view Subspace Clustering in Linear Time](https://mlsanity.com/paper/1911.09290/) (2019)
- [Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit](https://mlsanity.com/paper/1507.01238/) (2015)
- [Robust and Efficient Subspace Segmentation via Least Squares Regression](https://mlsanity.com/paper/1404.6736/) (2014)
- [Oracle Based Active Set Algorithm for Scalable Elastic Net Subspace Clustering](https://mlsanity.com/paper/1605.02633/) (2016)
- [Subspace Clustering by Block Diagonal Representation](https://mlsanity.com/paper/1805.09243/) (2018)
- [Self-Supervised Convolutional Subspace Clustering Network](https://mlsanity.com/paper/1905.00149/) (2019)
- [Structured Graph Learning for Scalable Subspace Clustering: From Single-view to Multi-view](https://mlsanity.com/paper/2102.07943/) (2021)
- [Pseudo-supervised Deep Subspace Clustering](https://mlsanity.com/paper/2104.03531/) (2021)
- [Stochastic Sparse Subspace Clustering](https://mlsanity.com/paper/2005.01449/) (2020)
- [Scalable Deep k-Subspace Clustering](https://mlsanity.com/paper/1811.01045/) (2018)
- [Doubly Stochastic Subspace Clustering](https://mlsanity.com/paper/2011.14859/) (2020)
- [Spectral Clustering via Ensemble Deep Autoencoder Learning (SC-EDAE)](https://mlsanity.com/paper/1901.02291/) (2019)

## Abstract (arXiv)

Subspace clustering methods face inherent scalability limits due to the O(n3) cost (with n denoting the number of data samples) of constructing full n× n affinities and performing spectral decomposition. While deep learning-based approaches improve feature extraction, they maintain this computational bottleneck through exhaustive pairwise similarity computations. We propose SDSNet (Scalable Deep Subspace Network), a deep subspace clustering framework that achieves O(n) complexity through (1) landmark-based approximation, avoiding full affinity matrices, (2) joint optimization of auto-encoder reconstruction with self-expression objectives, and (3) direct spectral clustering on factorized representations. The framework combines convolutional auto-encoders with subspace-preserving constraints. Experimental results demonstrate that SDSNet achieves comparable clustering quality to state-of-the-art methods with significantly improved computational efficiency.