CausalVAE: Structured Causal Disentanglement in Variational Autoencoder
read the original abstract
Learning disentanglement aims at finding a low dimensional representation which consists of multiple explanatory and generative factors of the observational data. The framework of variational autoencoder (VAE) is commonly used to disentangle independent factors from observations. However, in real scenarios, factors with semantics are not necessarily independent. Instead, there might be an underlying causal structure which renders these factors dependent. We thus propose a new VAE based framework named CausalVAE, which includes a Causal Layer to transform independent exogenous factors into causal endogenous ones that correspond to causally related concepts in data. We further analyze the model identifiabitily, showing that the proposed model learned from observations recovers the true one up to a certain degree by providing supervision signals (e.g. feature labels). Experiments are conducted on various datasets, including synthetic and real word benchmark CelebA. Results show that the causal representations learned by CausalVAE are semantically interpretable, and their causal relationship as a Directed Acyclic Graph (DAG) is identified with good accuracy. Furthermore, we demonstrate that the proposed CausalVAE model is able to generate counterfactual data through "do-operation" to the causal factors.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
Show Me Examples: Inferring Visual Concepts from Image Sets
Introduces VICIS task and training framework for inferring visual concepts from image sets, with experiments showing better accuracy, diversity, and generalization than standard VLMs on synthetic and ImageNet data.
-
A Neuroimaging Simulation Framework for Developing and Evaluating Causal AI
A framework generates synthetic neuroimages with explicit causal control via volumetric ROI changes to produce ground-truth data for benchmarking causal AI in neuroimaging.
-
Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces Identifiability
Enforcing local orthogonality on the Jacobian of the generative mapping yields identifiability for general nonlinear models when the latent domain has full combinatorial support.
-
TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations
TCD-Arena is a new customizable testing framework that runs millions of experiments to map how 33 different assumption violations affect time series causal discovery methods and shows ensembles can boost overall robustness.
-
CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation
CARE-ECG unifies ECG representation learning, causal graph-based diagnosis, and counterfactual assessment in an agentic LLM pipeline to improve accuracy and explanation faithfulness.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.