Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks

TL;DR

This paper introduces SCIGAN, a novel GAN-based model for estimating counterfactual outcomes of continuous interventions, addressing a gap in causal inference and demonstrating improved performance on semi-synthetic data.

Contribution

The paper presents a new GAN architecture with a hierarchical discriminator for continuous interventions and provides theoretical support for its effectiveness.

Findings

SCIGAN outperforms existing models on semi-synthetic data

The hierarchical discriminator effectively captures continuous intervention structure

Theoretical analysis supports the GAN framework's application in this setting

Abstract

While much attention has been given to the problem of estimating the effect of discrete interventions from observational data, relatively little work has been done in the setting of continuous-valued interventions, such as treatments associated with a dosage parameter. In this paper, we tackle this problem by building on a modification of the generative adversarial networks (GANs) framework. Our model, SCIGAN, is flexible and capable of simultaneously estimating counterfactual outcomes for several different continuous interventions. The key idea is to use a significantly modified GAN model to learn to generate counterfactual outcomes, which can then be used to learn an inference model, using standard supervised methods, capable of estimating these counterfactuals for a new sample. To address the challenges presented by shifting to continuous interventions, we propose a novel architecture for our discriminator - we build a hierarchical discriminator that leverages the structure of the continuous intervention setting. Moreover, we provide theoretical results to support our use of the GAN framework and of the hierarchical discriminator. In the experiments section, we introduce a new semi-synthetic data simulation for use in the continuous intervention setting and demonstrate improvements over the existing benchmark models.