EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hyperbolic Prototype-Residual Autoencoder for Interpretable Generative Latent Organization

Hyunjong Lee, Jeongho Kwak iD

Sensors · 05.08.2026 · 26 (15) · 4957

DOI: 10.3390/s26154957 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 05.08.2026. Verfasst von Hyunjong Lee und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering and Computer Science, Daegu Gyeongbuk Institute of Science & Technology (DGIST), Daegu 42988, Republic of Korea. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Interpretable organization of latent spaces remains a central challenge in generative modeling. Most generative models rely on continuous latent variables, but the learned space often lacks an explicit structure that explains how samples are organized or how semantic variation can be controlled. This paper proposes a hyperbolic prototype-residual autoencoder that organizes generative latent representations using a fixed prototype tree embedded in the Poincaré ball. Each encoded sample is assigned to a prototype by hyperbolic distance, and the decoder reconstructs or generates images from a prototype-residual representation. The prototype serves as a semantic anchor, while the residual captures local instance-level variation around the selected prototype. The framework combines prototype semantic learning, MMD-based latent spreading, and structural regularizers to align encoder–decoder behavior with the predefined hyperbolic hierarchy. Prototype semantic learning encourages fixed prototypes to decode into representative visual anchors, while MMD encourages encoded samples to occupy broad regions of the hyperbolic latent space. Experiments on MNIST and CelebA show interpretable coarse-to-fine behavior through radial decoding and prototype decoding, suggesting that fixed hyperbolic prototype trees provide an effective scaffold for prototype-guided image reconstruction and generation.

Schlagwörter

Stichwörter der Autor:innen

Poincaré ballautoencoderhyperbolic latent spaceinterpretable generative modelingprototype learningprototype-guided generation

Autor:innen und Institutionen

  • Department of Electrical Engineering and Computer Science, Daegu Gyeongbuk Institute of Science & Technology (DGIST), Daegu 42988, Republic of Korea.
  • Department of Computer Science and Engineering, Korea University, Seoul 02841, Republic of Korea.

ORCID-Profile: Jeongho Kwak

Zitieren

APA

Lee, H., & Kwak, J. (2026). Hyperbolic Prototype-Residual Autoencoder for Interpretable Generative Latent Organization. Sensors, 26(15), 4957. https://doi.org/10.3390/s26154957

Vancouver

Lee H, Kwak J. Hyperbolic Prototype-Residual Autoencoder for Interpretable Generative Latent Organization. Sensors. 2026;26(15):4957. doi:10.3390/s26154957

BibTeX
@article{Lee2026,
  author = {Lee, Hyunjong and Kwak, Jeongho},
  title = {Hyperbolic Prototype-Residual Autoencoder for Interpretable Generative Latent Organization},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {15},
  pages = {4957},
  doi = {10.3390/s26154957}
}
Kostenlos starten →