Deep Counterfactual Networks with Propensity-Dropout

By Ahmed M. Alaa, Michael Weisz, Mihaela van der Schaar. 2017

94 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering, Causal Inference & Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

In Causal Inference & Discovery

Citations in the corpus

Time-series forecasting with deep learning: a survey (2020, background): “While a large class of deep learning methods exists for estimating causal effects in static settings [65, 66, 67], the key challenge in time series datasets is the presence of time-dependent confounding effects.”
Deconfounding Reinforcement Learning in Observational Settings (2018, background): “Causal inference is a fundamental notion in science and plays an increasingly important role in healthcare and medicine (Liu et al.; Soleimani et al., 2017; Schulam and Saria, 2017; Alaa et al., 2017; Alaa and van der Schaar, 2018; Atan et al., 2016).”
Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks (2020, methodology): “In the latter case, methods for handling the selection bias involve propensity weighting (Crump et al., 2008; Alaa et al., 2017; Shi et al., 2019), building sub-populations using tree based methods (Chipman et al.”
FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles (2019, background): “Counterfactual examples have been used in a variety of ML areas, such as reinforcement learning [23], deep learning [1], and explainable AI (XAI) [8, 13, 17, 18, 22, 24, 26, 28, 31, 35, 36].”
GENERATIVE ADVERSARIAL NETS (2018, methodology): “For instance, (1) in understanding the heterogeneous effects of drugs (Shalit et al. (2017); Alaa & van der Schaar (2017); Alaa et al. (2017)); (2) in evaluating the effect of a policy on unemployment rates (LaLonde (1986); Smith & Todd (2005)); (3) in verifying which factor causes a certain…”
Bayesian Nonparametric Causal Inference: Information Rates and Learning Algorithms (2017, methodology): “Instead, most previous works on causal effect inference have focused on model development, and various algorithms have been recently developed for estimating individualized treatment effects from observational data, mostly based on either treebased methods [7], [8], [16], or deep learning methods [1”