Wendong Liang — accepted AI-conference papers

2023

Causal Component Analysis

Wendong Liang, Armin Kekić, Julius von Kügelgen, Simon Buchholz, Michel Besserve, Luigi Gresele +1

NeurIPS 2023poster

Independent Component Analysis (ICA) aims to recover independent latent variables from observed mixtures thereof. Causal Representation Learning (CRL) aims instead to infer causally related (thus often statistically _dependent_) latent variables, together with the unknown graph encoding their causal…

Cited by 45 Source ↗PDF ↗code ↗Scholar ↗

2023

Nonparametric Identifiability of Causal Representations from Unknown Interventions

Julius von Kügelgen, Michel Besserve, Wendong Liang, Luigi Gresele, Armin Kekić, Elias Bareinboim +2

NeurIPS 2023poster

We study causal representation learning, the task of inferring latent causal variables and their causal relations from high-dimensional functions (“mixtures”) of the variables. Prior work relies on weak supervision, in the form of counterfactual pre- and post-intervention views or temporal structure…

Cited by 70 Source ↗PDF ↗code ↗Scholar ↗