Linear Causal Representation Learning from Unknown Multi-node Interventions

• URL: http://arxiv.org/abs/2406.05937v2
• Date: Thu, 05 Dec 2024 03:16:26 GMT
• Title: Linear Causal Representation Learning from Unknown Multi-node Interventions
• Abstract summary: It is established that given sufficiently diverse interventional environments, identifiability up to ancestors is possible using only soft interventions.<n>Remarkably, these guarantees match the best-known results for more restrictive single-node interventions.
• Score: 29.21757873428357
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the multifaceted recent advances in interventional causal representation learning (CRL), they primarily focus on the stylized assumption of single-node interventions. This assumption is not valid in a wide range of applications, and generally, the subset of nodes intervened in an interventional environment is fully unknown. This paper focuses on interventional CRL under unknown multi-node (UMN) interventional environments and establishes the first identifiability results for general latent causal models (parametric or nonparametric) under stochastic interventions (soft or hard) and linear transformation from the latent to observed space. Specifically, it is established that given sufficiently diverse interventional environments, (i) identifiability up to ancestors is possible using only soft interventions, and (ii) perfect identifiability is possible using hard interventions. Remarkably, these guarantees match the best-known results for more restrictive single-node interventions. Furthermore, CRL algorithms are also provided that achieve the identifiability guarantees. A central step in designing these algorithms is establishing the relationships between UMN interventional CRL and score functions associated with the statistical models of different interventional environments. Establishing these relationships also serves as constructive proof of the identifiability guarantees.

Related papers

• Causal Gaussian Processes for Robust Treatment Effect Evaluation with Unobserved Confounding [65.76392290956525]
  This paper investigates causal effect evaluation over the continuous domain from confounded observations.<n>We develop a novel family of Causal Gaussian process (CGP) models that effectively approximate the observational and interventional distributions of any causal model with confounded observations.
  arXiv  Detail & Related papers  (2026-06-20T00:05:25Z)
• Latent Confounded Causal Discovery via Lie Bracket Geometry [1.3295383263113112]
  This paper introduces two causal discovery algorithms under latent confounding.<n>BRIDGE and Spectral Kan-Do Flow Matching learn intervention fields and factors latent curvature spectrally.<n>A detailed set of experiments show that both algorithms are capable of discovering causal models with latent confounders.
  arXiv  Detail & Related papers  (2026-06-17T21:31:16Z)
• Deriving Causal Order from Single-Variable Interventions: Guarantees & Algorithm [14.980926991441345]
  We show that datasets containing interventional data can be effectively extracted under realistic assumptions about the data distribution. We introduce interventional faithfulness, which relies on comparisons between the marginal distributions of each variable across observational and interventional settings. We also introduce Intersort, an algorithm designed to infer the causal order from datasets containing large numbers of single-variable interventions.
  arXiv  Detail & Related papers  (2024-05-28T16:07:17Z)
• A General Causal Inference Framework for Cross-Sectional Observational Data [0.4972323953932129]
  General Causal Inference (GCI) framework specifically designed for cross-sectional observational data. This paper proposes a GCI framework specifically designed for cross-sectional observational data.
  arXiv  Detail & Related papers  (2024-04-28T14:26:27Z)
• Causal Discovery under Off-Target Interventions [18.92683981229985]
  Causal graph discovery is a significant problem with applications across various disciplines. This work addresses the causal discovery problem under the setting of interventions with the natural goal of minimizing the number of interventions performed.
  arXiv  Detail & Related papers  (2024-02-13T05:43:49Z)
• Score-based Causal Representation Learning: Linear and General Transformations [31.786444957887472]
  The paper addresses both the identifiability and achievability aspects. It designs a score-based class of algorithms that ensures both identifiability and achievability. Results are validated via experiments on structured synthetic data and image data.
  arXiv  Detail & Related papers  (2024-02-01T18:40:03Z)
• Bayesian causal discovery from unknown general interventions [55.2480439325792]
  We consider the problem of learning causal Directed Acyclic Graphs (DAGs) using combinations of observational and interventional experimental data. We develop a Markov Chain Monte Carlo scheme to approximate the posterior distribution over DAGs, intervention targets and induced parent sets.
  arXiv  Detail & Related papers  (2023-12-01T11:30:51Z)
• Identifying Linearly-Mixed Causal Representations from Multi-Node Interventions [14.586959818386765]
  We provide the first identifiability result for causal representation learning that allows for multiple variables to be targeted by an intervention within one environment. Our approach hinges on a general assumption on the coverage and diversity of interventions across environments. In addition to and inspired by our theoretical contributions, we present a practical algorithm to learn causal representations from multi-node interventional data.
  arXiv  Detail & Related papers  (2023-11-05T16:05:00Z)
• General Identifiability and Achievability for Causal Representation Learning [33.80247458590611]
  The paper establishes identifiability and achievability results using two hard uncoupled interventions per node in the latent causal graph. For identifiability, the paper establishes that perfect recovery of the latent causal model and variables is guaranteed under uncoupled interventions. The analysis, additionally, recovers the identifiability result for two hard coupled interventions, that is when metadata about the pair of environments that have the same node intervened is known.
  arXiv  Detail & Related papers  (2023-10-24T01:47:44Z)
• Provably Efficient UCB-type Algorithms For Learning Predictive State Representations [55.00359893021461]
  The sequential decision-making problem is statistically learnable if it admits a low-rank structure modeled by predictive state representations (PSRs) This paper proposes the first known UCB-type approach for PSRs, featuring a novel bonus term that upper bounds the total variation distance between the estimated and true models. In contrast to existing approaches for PSRs, our UCB-type algorithms enjoy computational tractability, last-iterate guaranteed near-optimal policy, and guaranteed model accuracy.
  arXiv  Detail & Related papers  (2023-07-01T18:35:21Z)
• Learning Linear Causal Representations from Interventions under General Nonlinear Mixing [52.66151568785088]
  We prove strong identifiability results given unknown single-node interventions without access to the intervention targets. This is the first instance of causal identifiability from non-paired interventions for deep neural network embeddings.
  arXiv  Detail & Related papers  (2023-06-04T02:32:12Z)
• Nonparametric Identifiability of Causal Representations from Unknown Interventions [63.1354734978244]
  We study causal representation learning, the task of inferring latent causal variables and their causal relations from mixtures of the variables. Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data.
  arXiv  Detail & Related papers  (2023-06-01T10:51:58Z)
• Scalable Intervention Target Estimation in Linear Models [52.60799340056917]
  Current approaches to causal structure learning either work with known intervention targets or use hypothesis testing to discover the unknown intervention targets. This paper proposes a scalable and efficient algorithm that consistently identifies all intervention targets. The proposed algorithm can be used to also update a given observational Markov equivalence class into the interventional Markov equivalence class.
  arXiv  Detail & Related papers  (2021-11-15T03:16:56Z)
• Learning Neural Causal Models with Active Interventions [83.44636110899742]
  We introduce an active intervention-targeting mechanism which enables a quick identification of the underlying causal structure of the data-generating process. Our method significantly reduces the required number of interactions compared with random intervention targeting. We demonstrate superior performance on multiple benchmarks from simulated to real-world data.
  arXiv  Detail & Related papers  (2021-09-06T13:10:37Z)

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.