EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep clustering analysis via variational autoencoder with Gamma mixture latent embeddings

Jiaxun Guo, Wentao Fan, Manar Amayri, Nizar Bouguila

Neural Networks · 2025

DOI: 10.1016/j.neunet.2024.106979 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neural Networks, 2025. Verfasst von Jiaxun Guo und 3 weiteren Autor:innen. Beteiligte Einrichtung: CIISE, Concordia University, Montreal, H3G 1T7, QC, Canada. Electronic address: g_jiax@encs.concordia.ca. Hauptthemen laut MEDLINE: Neural Networks, Computer, Deep Learning. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province, Natural Sciences and Engineering Research Council of Canada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article proposes a novel deep clustering model based on the variational autoencoder (VAE), named GamMM-VAE, which can learn latent representations of training data for clustering in an unsupervised manner. Most existing VAE-based deep clustering methods use the Gaussian mixture model (GMM) as a prior on the latent space. We employ a more flexible asymmetric Gamma mixture model to achieve higher quality embeddings of the data latent space. Second, since the Gamma is defined for strictly positive variables, in order to exploit the reparameterization trick of VAE, we propose a transformation method from Gaussian distribution to Gamma distribution. This method can also be considered a Gamma distribution reparameterization trick, allows gradients to be backpropagated through the sampling process in the VAE. Finally, we derive the evidence lower bound (ELBO) based on the Gamma mixture model in an effective way for the stochastic gradient variational Bayesian (SGVB) estimator to optimize the proposed model. ELBO, a variational inference objective, ensures the maximization of the approximation of the posterior distribution, while SGVB is a method used to perform efficient inference and learning in VAEs. We validate the effectiveness of our model through quantitative comparisons with other state-of-the-art deep clustering models on six benchmark datasets. Moreover, due to the generative nature of VAEs, the proposed model can generate highly realistic samples of specific classes without supervised information.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerDeep LearningCluster AnalysisBayes TheoremNormal DistributionHumansAlgorithmsAutoencoder

Stichwörter der Autor:innen

ClusteringData augmentationGamma mixture modelsVAEVariational inference

Autor:innen und Institutionen

  • CIISE, Concordia University, Montreal, H3G 1T7, QC, Canada. Electronic address: g_jiax@encs.concordia.ca.
  • Guangdong Provincial Key Laboratory IRADS and Department of Computer Science, Beijing Normal University-Hong Kong Baptist University United International College, Zhuhai, Guangdong, China. Electronic address: wentaofan@…
  • CIISE, Concordia University, Montreal, H3G 1T7, QC, Canada. Electronic address: manar.amayri@concordia.ca.
  • CIISE, Concordia University, Montreal, H3G 1T7, QC, Canada. Electronic address: nizar.bouguila@concordia.ca.

Förderung

  • National Natural Science Foundation of China
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Natural Sciences and Engineering Research Council of Canada

Zitieren

APA

Guo, J., Fan, W., Amayri, M., & Bouguila, N. (2025). Deep clustering analysis via variational autoencoder with Gamma mixture latent embeddings. Neural Networks. https://doi.org/10.1016/j.neunet.2024.106979

Vancouver

Guo J, Fan W, Amayri M, Bouguila N. Deep clustering analysis via variational autoencoder with Gamma mixture latent embeddings. Neural Networks. 2025. doi:10.1016/j.neunet.2024.106979

BibTeX
@article{Guo2025,
  author = {Guo, Jiaxun and Fan, Wentao and Amayri, Manar and Bouguila, Nizar},
  title = {Deep clustering analysis via variational autoencoder with Gamma mixture latent embeddings},
  journal = {Neural Networks},
  year = {2025},
  doi = {10.1016/j.neunet.2024.106979}
}
Kostenlos starten →