RepFlow: Representation Enhanced Flow Matching for Causal Effect Estimation

TL;DR

RepFlow is a novel framework that combines representation learning with flow matching to improve causal effect estimation from observational data, addressing bias and distribution modeling limitations.

Contribution

It introduces a joint optimization approach integrating representation learning with Conditional Flow Matching, enhancing causal inference accuracy and stability.

Findings

RepFlow outperforms existing methods in point causal effect estimation.

RepFlow effectively models the distribution of potential outcomes.

The framework reduces selection bias through Wasserstein distance minimization.

Abstract

Estimating causal effects from observational data has become increasingly critical in diverse fields including healthcare, economics, and social policy. The fundamental challenge in causal inference arises from the missing counterfactuals and the selection bias. Existing methods are largely limited to point estimates and lack the capacity for distribution modeling. In this work, we propose RepFlow, a novel framework that formulates causal effect estimation as a joint optimization problem integrating representation learning with Conditional Flow Matching (CFM). RepFlow mitigates selection bias by minimizing the entropically regularized Wasserstein distance between treated and control representations. To enhance numerical stability, we further introduce an $L_2$ normalization constraint on latent representations. This balanced representation enables the flow model to accurately capture the distribution of potential outcomes. Extensive experiments across a wide range of benchmarks demonstrate that RepFlow consistently outperforms existing methods in both point and distributional causal effect estimation.