Deep Counterfactual Networks with Propensity-Dropout

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.

References in corpus (3)

• Adam: A Method for Stochastic Optimization
• Recursive Partitioning for Heterogeneous Causal Effects
• A Bayesian Nonparametric Approach for Estimating Individualized Treatment-Response Curves

Cited by in corpus (17)

• Time Series Forecasting With Deep Learning: A Survey
• Perfect Match: A Simple Method for Learning Representations For Counterfactual Inference With Neural Networks
• Adapting Neural Networks for the Estimation of Treatment Effects
• Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks
• Deconfounding Reinforcement Learning in Observational Settings
• Bayesian Nonparametric Causal Inference: Information Rates and Learning Algorithms
• A Survey on Causal Inference
• Unveiling the frontiers of deep learning: innovations shaping diverse domains
• On Inductive Biases for Heterogeneous Treatment Effect Estimation
• G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes
• Adapting Neural Networks for Uplift Models
• Assisting Clinical Decisions for Scarcely Available Treatment via Disentangled Latent Representation
• Learning Matching Representations for Individualized Organ Transplantation Allocation
• Representation Learning for Integrating Multi-domain Outcomes to Optimize Individualized Treatments
• Balance Regularized Neural Network Models for Causal Effect Estimation
• The Bias-Variance Tradeoff of Doubly Robust Estimator with Targeted $L_1$ regularized Neural Networks Predictions
• Estimating Potential Outcome Distributions with Collaborating Causal Networks