Diffusion-Based Causal Representation Learning
Entropy · 28.06.2024 · 26 (7) · 556
DOI: 10.3390/e26070556 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 28.06.2024. Verfasst von Amir Mohammad Karimi Mamaghan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Division of Decision and Control Systems (DCS), KTH Royal Institute of Technology, 114 28 Stockholm, Sweden. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Causal reasoning can be considered a cornerstone of intelligent systems. Having access to an underlying causal graph comes with the promise of cause–effect estimation and the identification of efficient and safe interventions. However, learning causal representations remains a major challenge, due to the complexity of many real-world systems. Previous works on causal representation learning have mostly focused on Variational Auto-Encoders (VAEs). These methods only provide representations from a point estimate, and they are less effective at handling high dimensions. To overcome these problems, we propose a Diffusion-based Causal Representation Learning (DCRL) framework which uses diffusion-based representations for causal discovery in the latent space. DCRL provides access to both single-dimensional and infinite-dimensional latent codes, which encode different levels of information. In a first proof of principle, we investigate the use of DCRL for causal representation learning in a weakly supervised setting. We further demonstrate experimentally that this approach performs comparably well in identifying the latent causal structure and causal variables.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Decision and Control Systems (DCS), KTH Royal Institute of Technology, 114 28 Stockholm, Sweden.
- Helmholtz AI, 85764 Munich, Germany.
- MPI for Intelligent Systems, 72076 Tübingen, Germany.
- School of Computation, Information and Technology, TU Munich, 80333 Munich, Germany.
- Digital Futures, 114 28 Stockholm, Sweden.
- Department of Computer Science, University of Oxford, Oxford OX1 2JD, UK.
ORCID-Profile: Amir Mohammad Karimi Mamaghan
Zitieren
APA
Karimi Mamaghan, A. M., Dittadi, A., Bauer, S., Johansson, K. H., & Quinzan, F. (2024). Diffusion-Based Causal Representation Learning. Entropy, 26(7), 556. https://doi.org/10.3390/e26070556
Vancouver
Karimi Mamaghan AM, Dittadi A, Bauer S, Johansson KH, Quinzan F. Diffusion-Based Causal Representation Learning. Entropy. 2024;26(7):556. doi:10.3390/e26070556
BibTeX
@article{KarimiMamaghan2024,
author = {Karimi Mamaghan, Amir Mohammad and Dittadi, Andrea and Bauer, Stefan and Johansson, Karl Henrik and Quinzan, Francesco},
title = {Diffusion-Based Causal Representation Learning},
journal = {Entropy},
year = {2024},
volume = {26},
number = {7},
pages = {556},
doi = {10.3390/e26070556}
}
EUVIMED