Score-based Causal Representation Learning: Linear and General
Transformations
- URL: http://arxiv.org/abs/2402.00849v2
- Date: Mon, 26 Feb 2024 21:30:37 GMT
- Title: Score-based Causal Representation Learning: Linear and General
Transformations
- Authors: Burak Var{\i}c{\i}, Emre Acart\"urk, Karthikeyan Shanmugam, Abhishek
Kumar, Ali Tajer
- Abstract summary: The paper addresses both the identifiability and achievability aspects.
It designs a score-based class of algorithms that ensures both identifiability and achievability.
- Score: 35.82689499120426
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper addresses intervention-based causal representation learning (CRL)
under a general nonparametric latent causal model and an unknown transformation
that maps the latent variables to the observed variables. Linear and general
transformations are investigated. The paper addresses both the identifiability
and achievability aspects. Identifiability refers to determining
algorithm-agnostic conditions that ensure recovering the true latent causal
variables and the latent causal graph underlying them. Achievability refers to
the algorithmic aspects and addresses designing algorithms that achieve
identifiability guarantees. By drawing novel connections between score
functions (i.e., the gradients of the logarithm of density functions) and CRL,
this paper designs a score-based class of algorithms that ensures both
identifiability and achievability. First, the paper focuses on linear
transformations and shows that one stochastic hard intervention per node
suffices to guarantee identifiability. It also provides partial identifiability
guarantees for soft interventions, including identifiability up to ancestors
for general causal models and perfect latent graph recovery for sufficiently
non-linear causal models. Secondly, it focuses on general transformations and
shows that two stochastic hard interventions per node suffice for
identifiability. Notably, one does not need to know which pair of
interventional environments have the same node intervened.
Related papers
- Identifiable Latent Polynomial Causal Models Through the Lens of Change [85.67870425656368]
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, known as identifiability.
arXiv Detail & Related papers (2023-10-24T07:46:10Z) - 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) - 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) - Score-based Causal Representation Learning with Interventions [54.735484409244386]
This paper studies the causal representation learning problem when latent causal variables are observed indirectly.
The objectives are: (i) recovering the unknown linear transformation (up to scaling) and (ii) determining the directed acyclic graph (DAG) underlying the latent variables.
arXiv Detail & Related papers (2023-01-19T18:39:48Z) - Effect Identification in Cluster Causal Diagrams [51.42809552422494]
We introduce a new type of graphical model called cluster causal diagrams (for short, C-DAGs)
C-DAGs allow for the partial specification of relationships among variables based on limited prior knowledge.
We develop the foundations and machinery for valid causal inferences over C-DAGs.
arXiv Detail & Related papers (2022-02-22T21:27:31Z) - The Proximal ID Algorithm [9.190358641395848]
Unobserved confounding is a fundamental obstacle to establishing valid causal conclusions from observational data.
We develop a synthesis of the former and latter approaches to identification in causal inference.
Our approach allows us to systematically exploit proxies to adjust for the presence of unobserved confounders.
arXiv Detail & Related papers (2021-08-15T21:32:47Z) - A Local Method for Identifying Causal Relations under Markov Equivalence [7.904790547594697]
Causality is important for designing interpretable and robust methods in artificial intelligence research.
We propose a local approach to identify whether a variable is a cause of a given target based on causal graphical models of directed acyclic graphs (DAGs)
arXiv Detail & Related papers (2021-02-25T05:01:44Z) - Structural Causal Models Are (Solvable by) Credal Networks [70.45873402967297]
Causal inferences can be obtained by standard algorithms for the updating of credal nets.
This contribution should be regarded as a systematic approach to represent structural causal models by credal networks.
Experiments show that approximate algorithms for credal networks can immediately be used to do causal inference in real-size problems.
arXiv Detail & Related papers (2020-08-02T11:19:36Z) - Semiparametric Inference For Causal Effects In Graphical Models With
Hidden Variables [13.299431908881425]
Identification theory for causal effects in causal models associated with hidden variable directed acyclic graphs is well studied.
corresponding algorithms are underused due to the complexity of estimating the identifying functionals they output.
We bridge the gap between identification and estimation of population-level causal effects involving a single treatment and a single outcome.
arXiv Detail & Related papers (2020-03-27T22:29:04Z)
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.