PuSH - Publication Server of Helmholtz Zentrum München

Karimi Mamaghan, A.M.* ; Dittadi, A. ; Bauer, S. ; Johansson, K.H.* ; Quinzan, F.*

Diffusion-based causal representation learning.

Entropy 26:556 (2024)
Publ. Version/Full Text DOI PMC
Open Access Gold
Creative Commons Lizenzvertrag
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.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Corresponding Author
Keywords Causal Representation Learning ; Diffusion Models ; Diffusion-based Representations ; Weak Supervision; Marginal Structural Models
e-ISSN 1099-4300
Journal Entropy
Quellenangaben Volume: 26, Issue: 7, Pages: , Article Number: 556 Supplement: ,
Publisher MDPI
Publishing Place St Alban-anlage 66, Ch-4052 Basel, Switzerland
Non-patent literature Publications
Reviewing status Peer reviewed
Institute(s) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Grants Wallenberg AI, Autonomous Systems and Software Program (WASP) - Knut and Alice Wallenberg Foundation