Identifiable Multimodal Causal Representation Learning under Partial Latent Sharing

• URL: http://arxiv.org/abs/2605.19135v1
• Date: Mon, 18 May 2026 21:34:29 GMT
• Title: Identifiable Multimodal Causal Representation Learning under Partial Latent Sharing
• Abstract summary: Causal representation learning seeks to uncover meaningful latent variables and their corresponding causal structure from observational data.<n>Proving identifiability in CRL is intrinsically difficult, and we address in this work an even more challenging setting: multimodality.<n>We consider multimodal observed data with a latent partially shared structure. Each modality is generated, through non linear mixing functions, from a specific subset of causal latent variables.<n>Our identifiability results, furthermore, apply to the undercomplete scenario where we have, for each modality, more observed than latent variables.
• Score: 4.400865943835067
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Causal representation learning (CRL) seeks to uncover meaningful latent variables and their corresponding causal structure from high-dimensional observational data. Although its significance, CRL identifiability remains a crucial property, as it ensures the recovery of the mechanisms behind the data generation process, and hence the interpretability and robustness of the representation. Proving identifiability in CRL is intrinsically difficult, and we address in this work an even more challenging setting: multimodality. We consider multimodal observed data with a latent partially shared structure. Each modality is generated, through non linear mixing functions, from a specific subset of causal latent variables. Under flexible assumptions and without imposing any parametric distribution on the latent variables, we establish component-wise identifiability guarantees for the causal latent representation. Our identifiability results, furthermore, apply to the undercomplete scenario where we have, for each modality, more observed than latent variables. To instantiate our theoretical analysis, we introduce a Wasserstein-based module to recover the partially shared latent structure. Due to its differentiability, the latter can be easily integrated into all types of architecture, only requiring minimal changes. Extensive experiments on synthetic and realistic datasets validate the superiority of our approach over SOTA methods.

Related papers

• All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs [61.02007370456733]
  We show that a single task can be supported by multiple, structurally distinct circuits or sheaves that are simultaneously faithful, sparse, and complete.<n>We propose a Distributive Circuit Hypothesis and provide a theoretical analysis demonstrating that non-unique, low-overlap circuit explanations arise naturally from high-dimensional superposition.
  arXiv  Detail & Related papers  (2026-05-12T19:21:23Z)
• Hierarchical Contrastive Learning for Multimodal Data [3.1788482285024107]
  Hierarchical Contrastive Learning is a framework that learns globally shared, partially shared, and modality-specific representations.<n>On multimodal electronic health records, HCL yields more informative representations and consistently improves predictive performance.
  arXiv  Detail & Related papers  (2026-04-07T05:53:04Z)
• DMMRL: Disentangled Multi-Modal Representation Learning via Variational Autoencoders for Molecular Property Prediction [7.709891405320469]
  We propose variational autoencoders to disentangle molecular representations into shared (structure-relevant) and private (modality-specific) latent spaces.<n>The proposed variational disentanglement mechanism effectively isolates the most informative features for property prediction.<n> Experimental validation across seven benchmark datasets demonstrates DMMRL's superior performance relative to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-03-22T07:53:08Z)
• Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning [80.44084021062105]
  We propose a novel latent partial causal model for multimodal data, featuring two latent coupled variables, connected by an undirected edge, to represent the transfer of knowledge across modalities.<n>Under specific statistical assumptions, we establish an identifiability result, demonstrating that representations learned by multimodal contrastive learning correspond to the latent coupled variables up to a trivial transformation.<n>Experiments on a pre-trained CLIP model embodies disentangled representations, enabling few-shot learning and improving domain generalization across diverse real-world datasets.
  arXiv  Detail & Related papers  (2024-02-09T07:18:06Z)
• Mapping the Multiverse of Latent Representations [17.2089620240192]
  PRESTO is a principled framework for mapping the multiverse of machine-learning models that rely on latent representations. Our framework uses persistent homology to characterize the latent spaces arising from different combinations of diverse machine-learning methods.
  arXiv  Detail & Related papers  (2024-02-02T15:54:53Z)
• Identifiable Latent Polynomial Causal Models Through the Lens of Change [82.14087963690561]
  Causal representation learning aims to unveil latent high-level causal representations from observed low-level data.<n>One of its primary tasks is to provide reliable assurance of identifying these latent causal models, known as identifiability.
  arXiv  Detail & Related papers  (2023-10-24T07:46:10Z)
• Latent Processes Identification From Multi-View Time Series [17.33428123777779]
  We propose a novel framework that employs the contrastive learning technique to invert the data generative process for enhanced identifiability. MuLTI integrates a permutation mechanism that merges corresponding overlapped variables by the establishment of an optimal transport formula.
  arXiv  Detail & Related papers  (2023-05-14T14:21:58Z)
• Latent Variable Representation for Reinforcement Learning [131.03944557979725]
  It remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of model-based reinforcement learning. We provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle. In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models.
  arXiv  Detail & Related papers  (2022-12-17T00:26:31Z)
• Learning Conditional Invariance through Cycle Consistency [60.85059977904014]
  We propose a novel approach to identify meaningful and independent factors of variation in a dataset. Our method involves two separate latent subspaces for the target property and the remaining input information. We demonstrate on synthetic and molecular data that our approach identifies more meaningful factors which lead to sparser and more interpretable models.
  arXiv  Detail & Related papers  (2021-11-25T17:33:12Z)
• A Critical View of the Structural Causal Model [89.43277111586258]
  We show that one can identify the cause and the effect without considering their interaction at all. We propose a new adversarial training method that mimics the disentangled structure of the causal model. Our multidimensional method outperforms the literature methods on both synthetic and real world datasets.
  arXiv  Detail & Related papers  (2020-02-23T22:52:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.