Google Research

Balance Regularized Neural Network Models for Causal Effect Estimation

  • Mehrdad Farajtabar
  • Andrew Lee
  • Yuanjian Feng
  • Vishal Gupta
  • Peter Dolan
  • Harish Chandran
  • Martin Szummer
Causal Discovery & Causality-Inspired Machine Learning Workshop, NeurIPS 2020 (2020)


Estimating individual and average treatment effects from observational data is an important problem in many domains such as healthcare and e-commerce. In this paper, we advocate balance regularization of multi-head neural network architectures. Our work is motivated by representation learning techniques to reduce differences between treated and untreated distributions that potentially arise due to confounding factors. We further regularize the model by encouraging it to predict control outcomes for individuals in the treatment group that are similar to control outcomes in the control group. We empirically study the bias-variance trade-off between different weightings of the regularizers, as well as between inductive and transductive inference.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work