Unified Embedding and Clustering

Abstract

In this paper, we introduce a novel algorithm that unifies manifold embedding and clustering (UEC) which efficiently predicts clustering assignments of the high dimensional data points in a new embedding space. The algorithm is based on a bi-objective optimisation problem combining embedding and clustering loss functions. Such original formulation will allow to simultaneously preserve the original structure of the data in the embedding space and produce better clustering assignments. The experimental results using a number of real-world datasets show that UEC is competitive with the state-of-art clustering methods.

Unsupervised clustering reveals phenotypes of AKI in ICU Covid19 patients

“…To achieve this, we first selected AKI patients and started by reducing the dimension of the matrix of SHAP values previously calculated (104 patients x 10 predictors), using the Uniform Manifold Approximation and Projection (UMAP) method. This preliminary step has been shown to improve downstream clusterisation[31]. This two-dimension projection was finally clusterized by the unsupervised Density-Based Spatial Clustering of Application with Noise (DBSCAN) algorithm.…”

“…Finally, we did not apply the clustering algorithm on the raw dataset as did other groups[15–17]. , but rather on a dimensionally reduced space; a strategy that has been shown to improve the clustering performance[31].…”

Unsupervised convolutional variational autoencoder deep embedding clustering for Raman spectra

“…For calculating accuracy, after the visualisation dimension reduction by T-SNE and UMAP, the cluster assignment is obtained using another clustering method, such as K -means, GMM or DBSCAN, to determine the cluster accuracy ACC. 36,37 In spectroscopy, SOM is the most common unsupervised clustering algorithm that is based on an artificial neural network. 38 SOM based on a deep embedded network has also performed well in many cases.…”

“…In addition to CVDE, the detailed clustering performances of the other five methods on the MNIST dataset can be found in ref. 28, 29, 37, 39 and 41.…”