Causal Effect Inference for Structured Treatments
arXiv:2106.01939
Abstract
We address the estimation of conditional average treatment effects (CATEs) for structured treatments (e.g., graphs, images, texts). Given a weak condition on the effect, we propose the generalized Robinson decomposition, which (i) isolates the causal estimand (reducing regularization bias), (ii) allows one to plug in arbitrary models for learning, and (iii) possesses a quasi-oracle convergence guarantee under mild assumptions. In experiments with small-world and molecular graphs we demonstrate that our approach outperforms prior work in CATE estimation.
arXiv commentNeurIPS 2021 Camera-Ready submission
References in corpus (12)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Recursive Partitioning for Heterogeneous Causal Effects
- Fast Graph Representation Learning with PyTorch Geometric
- Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning
- Discussion on "Bayesian Regression Tree Models for Causal Inference: Regularization, Confounding, and Heterogeneous Effects" by Hahn, Murray and Carvalho
- Causal Effect Inference with Deep Latent-Variable Models
- Estimation of causal effects with multiple treatments: a review and new ideas
- Perfect Match: A Simple Method for Learning Representations For Counterfactual Inference With Neural Networks
- An Introduction to Proximal Causal Learning
- Invariant Representation Learning for Treatment Effect Estimation
- RealCause: Realistic Causal Inference Benchmarking
- GraphITE: Estimating Individual Effects of Graph-structured Treatments