IAE-ClusterGAN: A new Inverse autoencoder for Generative Adversarial Attention Clustering network

Clustering is a challenging and crucial task in unsupervised learning. Recently, though many clustering algorithms combined with deep learning have been proposed, we observe that the existing deep clustering algorithms do not considerably preserve the clustering structure and information of raw data...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) Vol. 465; pp. 406 - 416
Main Authors: Ling, Chao, Cao, Guitao, Cao, Wenming, Wang, Hong, Ren, He
Format: Journal Article
Language:English
Published: Elsevier B.V 20.11.2021
Subjects:
Attention mechanism
Clustering
Inverse autoencoder
Latent code
Unsupervised learning
Attention mechanism
Latent code
Inverse autoencoder
Clustering
Unsupervised learning
ISSN:0925-2312, 1872-8286
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Clustering is a challenging and crucial task in unsupervised learning. Recently, though many clustering algorithms combined with deep learning have been proposed, we observe that the existing deep clustering algorithms do not considerably preserve the clustering structure and information of raw data in the learned latent space. To address this issue, we propose a Generative Adversarial Attention Clustering network Based on Inverse autoencoder (IAE-ClusterGAN), which can control the distribution type of the learned latent code without additional constraints so that unsupervised clustering tasks can be done efficiently. Meanwhile, we integrate the attention mechanism into the network to make the latent code contain more useful clustering information. Moreover, we utilize hyperspherical mapping in the discriminator to improve the stability of model training and reduce the training parameters. Experimental results demonstrate that IAE-ClusterGAN achieves competitive results compared to the state-of-the-art models on five benchmark datasets.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2021.08.128