# Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms

arXiv: https://arxiv.org/abs/2502.20115 · HTML: https://mlsanity.com/paper/2502.20115/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 44 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Builds on (most cited first, 5 of 5)

- [Causal Discovery with General Non-Linear Relationships Using Non-Linear ICA](https://mlsanity.com/paper/1904.09096/) (2019)
- [Unpaired Multi-Domain Causal Representation Learning](https://mlsanity.com/paper/2302.00993/) (2023)
- [Independent Vector Analysis: Identification Conditions and Performance Bounds](https://mlsanity.com/paper/1303.7474/) (2013)
- [Shared Independent Component Analysis for Multi-Subject Neuroimaging](https://mlsanity.com/paper/2110.13502/) (2021)
- [Maturation Trajectories of Cortical Resting-State Networks Depend on the Mediating Frequency Band](https://mlsanity.com/paper/1803.04364/) (2018)

## Abstract (arXiv)

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.