Learning Structural Causal Models from Ordering: Identifiable Flow Models
This addresses causal inference for researchers and practitioners by providing a more efficient method for handling large structural causal models, though it is incremental as it builds on existing flow-based approaches.
The study tackled causal inference with observational data and a causal ordering by introducing flow models that recover transformations of exogenous variables, achieving state-of-the-art performance and reducing computational time compared to diffusion-based methods.
In this study, we address causal inference when only observational data and a valid causal ordering from the causal graph are available. We introduce a set of flow models that can recover component-wise, invertible transformation of exogenous variables. Our flow-based methods offer flexible model design while maintaining causal consistency regardless of the number of discretization steps. We propose design improvements that enable simultaneous learning of all causal mechanisms and reduce abduction and prediction complexity to linear O(n) relative to the number of layers, independent of the number of causal variables. Empirically, we demonstrate that our method outperforms previous state-of-the-art approaches and delivers consistent performance across a wide range of structural causal models in answering observational, interventional, and counterfactual questions. Additionally, our method achieves a significant reduction in computational time compared to existing diffusion-based techniques, making it practical for large structural causal models.