# Unsupervised Deep Embedding for Clustering Analysis

@article{Xie2016UnsupervisedDE, title={Unsupervised Deep Embedding for Clustering Analysis}, author={Junyuan Xie and Ross B. Girshick and Ali Farhadi}, journal={ArXiv}, year={2016}, volume={abs/1511.06335} }

Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms. [...] Key Method DEC learns a mapping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Our experimental evaluations on image and text corpora show significant improvement over state-of-the-art methods. Expand

#### Figures, Tables, and Topics from this paper

#### 1,143 Citations

Unsupervised Attention Embedding for Document Clustering

- Computer Science
- 2019

An Attention-based Deep Embedded Clustering (ADEC) algorithm is proposed to improve representation of data space and the performance and accuracy of document clustering is improved significantly using the ADEC clustering framework. Expand

Semi-supervised deep embedded clustering

- Computer Science
- Neurocomputing
- 2019

A new scheme of semi-supervised deep embedded clustering (SDEC) is proposed, which incorporates pairwise constraints in the feature learning process such that data samples belonging to the same cluster are close to each other and data samples belong to different clusters are far away from each other in the learned feature space. Expand

Deep Clustering for Unsupervised Learning of Visual Features

- Computer Science
- ECCV
- 2018

This work presents DeepCluster, a clustering method that jointly learns the parameters of a neural network and the cluster assignments of the resulting features and outperforms the current state of the art by a significant margin on all the standard benchmarks. Expand

Deep Continuous Clustering

- Mathematics, Computer Science
- ArXiv
- 2018

A clustering algorithm that performs nonlinear dimensionality reduction and clustering jointly is presented that outperforms state-of-the-art clustering schemes, including recent methods that use deep networks. Expand

Learning Statistical Representation with Joint Deep Embedded Clustering

- Computer Science
- ArXiv
- 2021

One of the most promising approaches for unsupervised learning is combining deep representation learning and deep clustering. Some recent works propose to simultaneously learn representation using… Expand

Meta Learning for Unsupervised Clustering

- Computer Science
- BMVC
- 2019

A novel meta learner, called MLC-Net, is proposed, which mimics numerous clustering tasks during the training to learn an effective embedding space for new clustering task, and achieves the state-of-the-art unsupervised clustering, as well as few-shot classification, performances. Expand

Semi-Supervised Clustering with Neural Networks

- Computer Science, Mathematics
- 2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM)
- 2020

A new loss function is defined that uses pairwise semantic similarity between objects combined with constrained k-means clustering to efficiently utilize both labeled and unlabeled data in the same framework. Expand

Improving spectral clustering with deep embedding, cluster estimation and metric learning

- Computer Science
- Knowl. Inf. Syst.
- 2021

This article generates the deep embedding via learning a deep autoencoder, which transforms the raw data into their lower dimensional representations suitable for clustering, and provides an effective method to estimate the number of clusters by learning a softmax autoen coder from thedeep embedding. Expand

Deep Discriminative Latent Space for Clustering

- Computer Science
- ArXiv
- 2018

The high accuracy obtained by the proposed auto-encoder with respect to a discriminative pairwise loss function during the auto-Encoder pre-training phase is demonstrated as well as its rapid convergence, even with small networks. Expand

Improving Spectral Clustering with Deep Embedding and Cluster Estimation

- Computer Science
- 2019 IEEE International Conference on Data Mining (ICDM)
- 2019

This paper provides an effective method to estimate the number of clusters by learning a softmax autoencoder from the deep embedding, and extends spectral clustering with the learned embedding and the estimated number. Expand

#### References

SHOWING 1-10 OF 45 REFERENCES

Learning Deep Representations for Graph Clustering

- Computer Science
- AAAI
- 2014

This work proposes a simple method, which first learns a nonlinear embedding of the original graph by stacked autoencoder, and then runs k-means algorithm on the embedding to obtain clustering result, which significantly outperforms conventional spectral clustering. Expand

The Challenges of Clustering High Dimensional Data

- Computer Science
- 2004

This chapter provides a short introduction to cluster analysis, and presents a brief overview of several recent techniques, including a more detailed description of recent work of recent which uses a concept-based clustering approach. Expand

Discriminative cluster analysis

- Computer Science, Mathematics
- ICML
- 2006

This paper proposes a new clustering algorithm called Discriminative Cluster Analysis (DCA), which jointly performs dimensionality reduction and clustering and shows the benefits of clustering in a low dimensional discriminative space rather than in the PC space (generative). Expand

Spectral Embedded Clustering: A Framework for In-Sample and Out-of-Sample Spectral Clustering

- Mathematics, Medicine
- IEEE Transactions on Neural Networks
- 2011

This paper proposes the spectral embedded clustering (SEC) framework, in which a linearity regularization is explicitly added into the objective function of SC methods, and presents a new Laplacian matrix constructed from a local regression of each pattern to capture both local and global discriminative information for clustering. Expand

An Analysis of Single-Layer Networks in Unsupervised Feature Learning

- Computer Science, Mathematics
- AISTATS
- 2011

The results show that large numbers of hidden nodes and dense feature extraction are critical to achieving high performance—so critical, in fact, that when these parameters are pushed to their limits, they achieve state-of-the-art performance on both CIFAR-10 and NORB using only a single layer of features. Expand

Unsupervised Feature Selection for the $k$-means Clustering Problem

- Computer Science, Mathematics
- NIPS
- 2009

It is proved that, if the authors run any γ-approximate k-means algorithm on the features selected using the algorithm presented, they can find a (1 + ( 1 + ∊) ≥)-approximates partition with high probability. Expand

Discriminative K-means for Clustering

- Computer Science, Mathematics
- NIPS
- 2007

It is shown in this paper that this iterative subspace selection and clustering is equivalent to kernel K-means with a specific kernel Gram matrix, which provides significant and new insights into the nature of this sub space selection procedure. Expand

Learning a Parametric Embedding by Preserving Local Structure

- Computer Science, Mathematics
- AISTATS
- 2009

The paper presents a new unsupervised dimensionality reduction technique, called parametric t-SNE, that learns a parametric mapping between the high-dimensional data space and the low-dimensional latent space, and evaluates the performance in experiments on three datasets. Expand

Distance Metric Learning with Application to Clustering with Side-Information

- Computer Science, Mathematics
- NIPS
- 2002

This paper presents an algorithm that, given examples of similar (and, if desired, dissimilar) pairs of points in �”n, learns a distance metric over ℝn that respects these relationships. Expand

Fast approximate spectral clustering

- Mathematics, Computer Science
- KDD
- 2009

This work develops a general framework for fast approximate spectral clustering in which a distortion-minimizing local transformation is first applied to the data, and develops two concrete instances of this framework, one based on local k-means clustering (KASP) and onebased on random projection trees (RASP). Expand