Log In Sign Up

Deep Clustering and Representation Learning that Preserves Geometric Structures

by   Lirong Wu, et al.

In this paper, we propose a novel framework for Deep Clustering and Representation Learning (DCRL) that preserves the geometric structure of data. In the proposed DCRL framework, the clustering of data points from different manifolds is done in the latent space guided by a clustering loss. To overcome the problem that clustering-oriented losses may deteriorate the geometric structure of embeddings in the latent space, two structure-oriented losses, namely an isometric loss and a ranking loss, are proposed to preserve intra-manifold structure locally and inter-manifold structure globally. Experimental results on various datasets show that the DCRL framework leads to comparable performances to current state-of-the-art deep clustering algorithms, yet exhibits superior performance for downstream tasks. Our results also demonstrate the importance and effectiveness of the proposed method in preserving geometric structure in terms of visualization and performance metrics.


page 14

page 17


Learning low bending and low distortion manifold embeddings

Autoencoders are a widespread tool in machine learning to transform high...

Improving k-Means Clustering Performance with Disentangled Internal Representations

Deep clustering algorithms combine representation learning and clusterin...

Clustering-Oriented Representation Learning with Attractive-Repulsive Loss

The standard loss function used to train neural network classifiers, cat...

Learning Robust Representation for Clustering through Locality Preserving Variational Discriminative Network

Clustering is one of the fundamental problems in unsupervised learning. ...

Relation-Guided Representation Learning

Deep auto-encoders (DAEs) have achieved great success in learning data r...

A deep learning approach to clustering visual arts

Clustering artworks is difficult for several reasons. On the one hand, r...

Deep Goal-Oriented Clustering

Clustering and prediction are two primary tasks in the fields of unsuper...