EUVIMEDEUVIMED entdecken
Crossref

Causal Flow-Based Variational Auto-Encoder for Disentangled Causal Representation Learning

Di Fan, Yannian Kou, Chuanhou Gao

ACM Transactions on Intelligent Systems and Technology · 31.10.2025 · 16 (5) · 1-26

DOI: 10.1145/3748660 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 18.09.2025. Verfasst von Di Fan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: National Nature Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Disentangled representation learning aims to learn low-dimensional representations where each dimension corresponds to an underlying generative factor. While the Variational Auto-Encoder (VAE) is widely used for this purpose, most existing methods assume independence among factors, a simplification that does not hold in many real-world scenarios where factors are often interdependent and exhibit causal relationships. To overcome this limitation, we propose the Disentangled Causal Variational Auto-Encoder (DCVAE), a novel supervised VAE framework that integrates causal flows into the representation learning process, enabling the learning of more meaningful and interpretable disentangled representations. We evaluate DCVAE on both synthetic and real-world datasets, demonstrating its superior ability in causal disentanglement and intervention experiments. Furthermore, DCVAE outperforms state-of-the-art methods in various downstream tasks, highlighting its potential for learning true causal structures among factors.

Förderung

  • National Nature Science Foundation of China

Zitieren

APA

Fan, D., Kou, Y., & Gao, C. (2025). Causal Flow-Based Variational Auto-Encoder for Disentangled Causal Representation Learning. ACM Transactions on Intelligent Systems and Technology, 16(5), 1-26. https://doi.org/10.1145/3748660

Vancouver

Fan D, Kou Y, Gao C. Causal Flow-Based Variational Auto-Encoder for Disentangled Causal Representation Learning. ACM Transactions on Intelligent Systems and Technology. 2025;16(5):1-26. doi:10.1145/3748660

BibTeX
@article{Fan2025,
  author = {Fan, Di and Kou, Yannian and Gao, Chuanhou},
  title = {Causal Flow-Based Variational Auto-Encoder for Disentangled Causal Representation Learning},
  journal = {ACM Transactions on Intelligent Systems and Technology},
  year = {2025},
  volume = {16},
  number = {5},
  pages = {1--26},
  doi = {10.1145/3748660}
}
Kostenlos starten →