Learning Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity
We study causal representation learning, the task of recovering high-level latent variables and their causal relationships in the form of a causal graph from low-level observed data (such as text and images), assuming access to observations generated from multiple environments. Prior results on the identifiability of causal representations typically assume access to single-node interventions which is rather unrealistic in practice, since the latent variables are unknown in the first place. In this work, we provide the first identifiability results based on data that stem from general environments. We show that for linear causal models, while the causal graph can be fully recovered, the latent variables are only identified up to the surrounded-node ambiguity (SNA) \citep{varici2023score}. We provide a counterpart of our guarantee, showing that SNA is basically unavoidable in our setting. We also propose an algorithm, \texttt{LiNGCReL} which provably recovers the ground-truth model up to SNA, and we demonstrate its effectiveness via numerical experiments. Finally, we consider general non-parametric causal models and show that the same identification barrier holds when assuming access to groups of soft single-node interventions.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningSimilar Papers 제목 키워드 기반
Beyond identifiability: Learning causal representations with few environments and finite samples
We provide explicit, finite-sample guarantees for learning causal representations from data with a sublinear number of environments. Causal representation learning seeks to provide a rigourous foundation for the general …
Representation LearningIdentifiable Latent Polynomial Causal Models Through the Lens of Change
Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of identifying these latent causal models, kn…
Representation LearningIdentifying Weight-Variant Latent Causal Models
The task of causal representation learning aims to uncover latent higher-level causal representations that affect lower-level observations. Identifying true latent causal representations from observed data, while allowin…
Representation LearningCITRIS: Causal Identifiability from Temporal Intervened Sequences
Understanding the latent causal factors of a dynamical system from visual observations is considered a crucial step towards agents reasoning in complex environments. In this paper, we propose CITRIS, a variational autoen…
Representation LearningTemporal SequencesGeneral Identifiability and Achievability for Causal Representation Learning
This paper focuses on causal representation learning (CRL) under a general nonparametric latent causal model and a general transformation model that maps the latent data to the observational data. It establishes identifi…
Representation Learning