Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912606806081536 |
|---|---|
| author | Heurtebise, Ambroise Chehab, Omar Ablin, Pierre Gramfort, Alexandre Hyvärinen, Aapo |
| author_facet | Heurtebise, Ambroise Chehab, Omar Ablin, Pierre Gramfort, Alexandre Hyvärinen, Aapo |
| contents | Causal discovery is a difficult problem that typically relies on strong assumptions on the data-generating model, such as non-Gaussianity. In practice, many modern applications provide multiple related views of the same system, which has rarely been considered for causal discovery. Here, we leverage this multi-view structure to achieve causal discovery with weak assumptions. We propose a multi-view linear Structural Equation Model (SEM) that extends the well-known framework of non-Gaussian disturbances by alternatively leveraging correlation over views. We prove the identifiability of the model for acyclic SEMs. Subsequently, we propose several multi-view causal discovery algorithms, inspired by single-view algorithms (DirectLiNGAM, PairwiseLiNGAM, and ICA-LiNGAM). The new methods are validated through simulations and applications on neuroimaging data, where they enable the estimation of causal graphs between brain regions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20115 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms Heurtebise, Ambroise Chehab, Omar Ablin, Pierre Gramfort, Alexandre Hyvärinen, Aapo Machine Learning 62R07 (Primary) 68T05, 05C82 (Secondary) I.2.6; I.5.1 Causal discovery is a difficult problem that typically relies on strong assumptions on the data-generating model, such as non-Gaussianity. In practice, many modern applications provide multiple related views of the same system, which has rarely been considered for causal discovery. Here, we leverage this multi-view structure to achieve causal discovery with weak assumptions. We propose a multi-view linear Structural Equation Model (SEM) that extends the well-known framework of non-Gaussian disturbances by alternatively leveraging correlation over views. We prove the identifiability of the model for acyclic SEMs. Subsequently, we propose several multi-view causal discovery algorithms, inspired by single-view algorithms (DirectLiNGAM, PairwiseLiNGAM, and ICA-LiNGAM). The new methods are validated through simulations and applications on neuroimaging data, where they enable the estimation of causal graphs between brain regions. |
| title | Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms |
| topic | Machine Learning 62R07 (Primary) 68T05, 05C82 (Secondary) I.2.6; I.5.1 |
| url | https://arxiv.org/abs/2502.20115 |