Deep k-Means: Jointly clustering with k-Means and learning representations

2018/06/26 by Maziar Moradi Fard, Fard, Maziar Moradi, Thibaut Thonet +4 · 3 citations
Computer Science · Mathematics · #FOS: Computer and information sciences #Face and Expression Recognition #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1806.10069

Under consideration at Pattern Recognition Letters

openalex publication_date 2018/06/26 · arxiv created 2018/12/12 · arxiv updated 2018/12/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/02

Abstract

We study in this paper the problem of jointly clustering and learning representations. As several previous studies have shown, learning representations that are both faithful to the data to be clustered and adapted to the clustering algorithm can lead to better clustering performance, all the more so that the two tasks are performed jointly. We propose here such an approach for k-Means clustering based on a continuous reparametrization of the objective function that leads to a truly joint solution. The behavior of our approach is illustrated on various datasets showing its efficacy in learning representations for objects while clustering them.

Citations

• Auto-Encoding Variational Bayes
• Joint Unsupervised Learning of Deep Representations and Image Clusters
• Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
• Categorical Reparameterization with Gumbel-Softmax
• Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
• Clustering with Deep Learning: Taxonomy and New Methods
• Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization

Cited by

• Classification EM-PCA for clustering and embedding
• Ensemble of Unsupervised Deep Learning for Clustering Imbalanced Tabular Data
• Multiple spheres detection problem—Center based clustering approach

Related

• Deep clustering with concrete k-means
• An Approach Towards Learning K-means-friendly Deep Latent Representation
• Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
• A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions
• Deep Embedded K-Means Clustering