• Home
  • Search
  • Improving deep representation learning for fuzzy clustering
  • https://doi.org/10.32657/10356/182967Copy DOI Icon

Improving deep representation learning for fuzzy clustering

  • Jan 1, 2024
  • Kang Song
Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

Deep clustering has gained popularity over the past decade due to the superior feature representation learning capability of deep neural networks. Many research works proposed novel approaches to improve the feature representation learning of the deep neural network for better clustering performance. The well-known Deep Embedded Clustering (DEC) method only focuses on its clustering loss which may distort the feature space learned by the autoencoder with reconstruction loss at the pre-training stage. The Improved DEC (IDEC) method preserves local structures in the feature space by adding back the decoder part and regularizing the clustering loss with reconstruction loss in the clustering training stage, but the effect is limited as the reconstruction loss used for regularization is the same as the one used in the pre-training stage. In the domain of deep fuzzy clustering, a common clustering loss term using KL divergence was adopted in many methods, including the well-known Graph-regularized Deep Normalized Fuzzy Compactness and Separation (GrDNFCS) method. However this loss term may have unpredictable adverse effects on the representation learning and clustering when batch size is small. The hard pseudo-label-based graph-regularization term in GrDNFCS has a strong bias towards the initial cluster assignments which makes the rectification of the representation learning difficult for ambiguous samples and samples around the cluster boundaries. In this thesis, we have proposed and presented some novel methods to improve the deep feature representation learning that can be applied to crisp clustering and fuzzy clustering to achieve better clustering performance. We proposed a novel method called Deep Embedded Clustering with Random Projection Penalty (DEC-RPP) which introduces a random projection penalty term in the loss functions as a regularizer to preserve pairwise distance and local structures in the feature space during training. The feature representation learned using this penalty term improves the clustering results significantly when compared with state-of-the-art methods using similar network architectures. We also proposed the Deep Fuzzy Clustering with Powered Membership and Soft Graph-regularization (pDFC-SoftGr) method that replaces the KL divergence loss term in GrDNFCS with our proposed powered membership loss term and replaces the hard pseudo-label-based graph-regularization term with our proposed soft graph-regularization term. We use examples to show the limitations of the loss terms in GrDNFCS and provide theoretical proof of the desired behavior of the powered membership term. The two new loss terms encourage the features learned by the deep neural network to produce strengthened fuzzy cluster assignments and make the rectification of ambiguous fuzzy cluster assignments easier. We conduct experiments on six benchmark datasets to compare the performance of our proposed method with other methods, we also conduct ablation studies on the effectiveness of each of the two new loss terms we proposed. The results show that both the ablation tests and the combined algorithm outperform other deep fuzzy clustering methods using similar network architectures. We also present a real-world application of deep fuzzy clustering in the E-commerce industry. The techniques that we proposed to improve deep feature representation learning are shown to be effective when used in this application.

Similar Papers
  • Research Article
  • Citations32

Deep Adaptive Fuzzy Clustering for Evolutionary Unsupervised Representation Learning.

  • May 01, 2024
  • IEEE Transactions on Neural Networks and Learning Systems
  • Dayu Tan +4
  • Conference Article
  • Citations627

Automated Vulnerability Detection in Source Code Using Deep Representation Learning

  • Dec 01, 2018
  • Rebecca Russell +7
  • Research Article
  • Citations97

AIMAFE: Autism spectrum disorder identification with multi-atlas deep feature representation and ensemble learning

  • Jul 09, 2020
  • Journal of Neuroscience Methods
  • Yufei Wang +4
  • Research Article
  • Citations327

Predicting Remaining Useful Life of Rolling Bearings Based on Deep Feature Representation and Transfer Learning

  • May 29, 2019
  • IEEE Transactions on Instrumentation and Measurement
  • Wentao Mao +2
  • PDF
  • Research Article
  • Citations23

Few-Shot Fine-Grained Image Classification: A Comprehensive Review

  • Mar 06, 2024
  • AI
  • Jie Ren +4
  • Research Article
  • Citations78

Deep Representation Learning with Target Coding

  • Mar 04, 2015
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Shuo Yang +4
  • Research Article
  • Citations31

Galaxy mergers in Subaru HSC-SSP: A deep representation learning approach for identification, and the role of environment on merger incidence

  • Nov 01, 2023
  • Astronomy & Astrophysics
  • Kiyoaki Christopher Omori +9
  • Research Article
  • Citations105

Deep Fusion Feature Representation Learning With Hard Mining Center-Triplet Loss for Person Re-Identification

  • Feb 07, 2020
  • IEEE Transactions on Multimedia
  • Cairong Zhao +5
  • Research Article
  • Citations4

Deep behavioural representation learning reveals risk profiles for malignant ventricular arrhythmias

  • Sep 16, 2024
  • npj Digital Medicine
  • Maarten Z H Kolk +10
  • Conference Article
  • Citations10

Action Recognition in the Dark via Deep Representation Learning

  • Dec 01, 2018
  • Anwaar Ulhaq
  • Research Article

Inflammatory marker-driven deep learning model for postoperative gastric cancer prognosis.

  • Jul 04, 2026
  • BMC medical informatics and decision making
  • Qinglan Zhu +4
  • Book Chapter

Deep Learning and Deep Knowledge Representation in the Human Brain

  • Aug 29, 2018
  • Nikola K Kasabov
  • Research Article

Deep Learning Representations of Programs: A Systematic Literature Review

  • Oct 08, 2025
  • ACM Computing Surveys
  • Deepika Shanmugasundaram +3
  • Book Chapter
  • Citations2

A Simple Deep Feature Representation for Person Re-identification

  • Jan 01, 2016
  • Shengke Wang +3
  • Research Article
  • Citations312

A Comprehensive Survey on Deep Graph Representation Learning

  • Feb 27, 2024
  • Neural Networks
  • Wei Ju +15
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.