PO-Flow: Flow-based Generative Models for Sampling Potential Outcomes and Counterfactuals
This addresses the need for individualized treatment predictions in healthcare, representing a novel method for a known bottleneck in causal inference.
The paper tackles the problem of predicting potential and counterfactual outcomes from observational data for clinical decision-making, proposing PO-Flow, a continuous normalizing flow framework that outperforms modern baselines across diverse datasets and causal tasks.
Predicting potential and counterfactual outcomes from observational data is central to clinical decision-making, where physicians must weigh treatments for an individual patient rather than relying solely on average effects at the population level. We propose PO-Flow, a continuous normalizing flow (CNF) framework for causal inference that jointly models potential outcomes and counterfactuals. Trained via flow matching, PO-Flow provides a unified approach to average treatment effect estimation, individualized potential outcome prediction, and counterfactual prediction. Besides, PO-Flow directly learns the densities of potential outcomes, enabling likelihood-based evaluation of predictions. Furthermore, PO-Flow explores counterfactual outcome generation conditioned on the observed factual in general observational datasets, with a supporting recovery result under certain assumptions. PO-Flow outperforms modern baselines across diverse datasets and causal tasks in the potential outcomes framework.