arrow
Return

Deep Multirepresentation Learning for Data Clustering

delete2024-11-01
delete2
delete
OA
AI
M
Mohammadreza Sadeghi *
N
Narges Armanfard
DOI:10.1109/TNNLS.2023.3289158delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
Deep clustering incorporates embedding into clustering in order to find a lower-dimensional space suitable for clustering tasks. Conventional deep clustering methods aim to obtain a single global embedding subspace (aka latent space) for all the data clusters. In contrast, in this article, we propose a deep multirepresentation learning (DML) framework for data clustering whereby each difficult-to-cluster data group is associated with its own distinct optimized latent space and all the easy-to-cluster data groups are associated with a general common latent space. Autoencoders (AEs) are employed for generating cluster-specific and general latent spaces. To specialize each AE in its associated data cluster(s), we propose a novel and effective loss function which consists of weighted reconstruction and clustering losses of the data points, where higher weights are assigned to the samples more probable to belong to the corresponding cluster(s). Experimental results on benchmark datasets demonstrate that the proposed DML framework and loss function outperform state-of-the-art clustering approaches. In addition, the results show that the DML method significantly outperforms the SOTA on imbalanced datasets as a result of assigning an individual latent space to the difficult clusters.
Keywords:
Clustering algorithms
Training
Task analysis
Decoding
Optimization
Learning systems
Image reconstruction
Autoencoder (AE)
cluster-specific AEs
data clustering
multiple representation learning

Journal

IEEE Transactions on Neural Networks and Learning Systems cover
IEEE Transactions on Neural Networks and Learning Systems
IF:
8.9
Papers:
7.5K
Citations:
7.2W

Organization

M
McGill University
Scholars:
5.5W
Papers: 4.9W
Citations: 7.0W