# Deep Unsupervised Clustering Using Mixture of Autoencoders

arXiv: https://arxiv.org/abs/1712.07788 · HTML: https://mlsanity.com/paper/1712.07788/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2017.

## Built on by (most cited first, 9 of 9)

- [Supporting Clustering with Contrastive Learning](https://mlsanity.com/paper/2103.12953/) (2021)
- [MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering](https://mlsanity.com/paper/2105.01899/) (2021)
- [You Never Cluster Alone](https://mlsanity.com/paper/2106.01908/) (2021)
- [Exploring Expert Specialization through Unsupervised Training in Sparse Mixture of Experts](https://mlsanity.com/paper/2509.10025/) (2025)
- [Mixture-of-Experts Variational Autoencoder for Clustering and Generating from Similarity-Based Representations on Single Cell Data](https://mlsanity.com/paper/1910.07763/) (2019)
- [Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction](https://mlsanity.com/paper/2303.05034/) (2023)
- [SMIXAE: Towards Unsupervised Manifold Discovery in Language Models](https://mlsanity.com/paper/2605.09224/) (2026)
- [Discret2Di -- Deep Learning based Discretization for Model-based Diagnosis](https://mlsanity.com/paper/2311.03413/) (2023)
- [Rethinking Structural Anomaly Detection: From Decision Boundaries to Projection Operators](https://mlsanity.com/paper/2606.15280/) (2026)

## Abstract (arXiv)

Unsupervised clustering is one of the most fundamental challenges in machine learning. A popular hypothesis is that data are generated from a union of low-dimensional nonlinear manifolds; thus an approach to clustering is identifying and separating these manifolds. In this paper, we present a novel approach to solve this problem by using a mixture of autoencoders. Our model consists of two parts: 1) a collection of autoencoders where each autoencoder learns the underlying manifold of a group of similar objects, and 2) a mixture assignment neural network, which takes the concatenated latent vectors from the autoencoders as input and infers the distribution over clusters. By jointly optimizing the two parts, we simultaneously assign data to clusters and learn the underlying manifolds of each cluster.