Deep Counterfactual Networks with Propensity-Dropout

TL;DR

This paper introduces a deep multitask learning framework with propensity-dropout regularization to improve causal effect inference from observational data, effectively addressing selection bias and outperforming existing methods.

Contribution

It presents a novel deep counterfactual network architecture that models potential outcomes with shared and outcome-specific layers, incorporating propensity-dropout to mitigate bias.

Findings

Outperforms state-of-the-art causal inference methods on real-world data

Effectively reduces bias caused by selection in observational datasets

Demonstrates improved accuracy in estimating individualized treatment effects

Abstract

We propose a novel approach for inferring the individualized causal effects of a treatment (intervention) from observational data. Our approach conceptualizes causal inference as a multitask learning problem; we model a subject's potential outcomes using a deep multitask network with a set of shared layers among the factual and counterfactual outcomes, and a set of outcome-specific layers. The impact of selection bias in the observational data is alleviated via a propensity-dropout regularization scheme, in which the network is thinned for every training example via a dropout probability that depends on the associated propensity score. The network is trained in alternating phases, where in each phase we use the training examples of one of the two potential outcomes (treated and control populations) to update the weights of the shared layers and the respective outcome-specific layers. Experiments conducted on data based on a real-world observational study show that our algorithm outperforms the state-of-the-art.