EUVIMEDEUVIMED entdecken
Crossref

Autoencoder in Autoencoder Networks

Changqing Zhang, Yu Geng, Zongbo Han, Yeqing Liu, Huazhu Fu, Qinghua Hu

IEEE Transactions on Neural Networks and Learning Systems · 2024-02 · 35 (2) · 2263-2275

DOI: 10.1109/tnnls.2022.3189239 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Neural Networks and Learning Systems, 2024-02. Verfasst von Changqing Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Natural Science Foundation of Tianjin.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modeling complex correlations on multiview data is still challenging, especially for high-dimensional features with possible noise. To address this issue, we propose a novel unsupervised multiview representation learning (UMRL) algorithm, termed autoencoder in autoencoder networks (AE2-Nets). The proposed framework effectively encodes information from high-dimensional heterogeneous data into a compact and informative representation with the proposed bidirectional encoding strategy. Specifically, the proposed AE2-Nets conduct encoding in two directions: the inner-AE-networks extract view-specific intrinsic information (forward encoding), while the outer-AE-networks integrate this view-specific intrinsic information from different views into a latent representation (backward encoding). For the nested architecture, we further provide a probabilistic explanation and extension from hierarchical variational autoencoder. The forward-backward strategy flexibly addresses high-dimensional (noisy) features within each view and encodes complementarity across multiple views in a unified framework. Extensive results on benchmark datasets validate the advantages compared to the state-of-the-art algorithms.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Natural Science Foundation of Tianjin
  • AISG Tech Challenge Funding

Zitieren

APA

Zhang, C., Geng, Y., Han, Z., Liu, Y., Fu, H., & Hu, Q. (2024). Autoencoder in Autoencoder Networks. IEEE Transactions on Neural Networks and Learning Systems, 35(2), 2263-2275. https://doi.org/10.1109/tnnls.2022.3189239

Vancouver

Zhang C, Geng Y, Han Z, Liu Y, Fu H, Hu Q. Autoencoder in Autoencoder Networks. IEEE Transactions on Neural Networks and Learning Systems. 2024;35(2):2263-2275. doi:10.1109/tnnls.2022.3189239

BibTeX
@article{Zhang2024,
  author = {Zhang, Changqing and Geng, Yu and Han, Zongbo and Liu, Yeqing and Fu, Huazhu and Hu, Qinghua},
  title = {Autoencoder in Autoencoder Networks},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  year = {2024},
  volume = {35},
  number = {2},
  pages = {2263--2275},
  doi = {10.1109/tnnls.2022.3189239}
}
Kostenlos starten →