Causal Effect Inference for Structured Treatments

2021/06/03 by Jean Kaddour, Kaddour, Jean, Yuchen Zhu +7 · 2 citations
Mathematics · #Advanced Causal Inference Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Statistical Methods and Inference #Statistical Methods in Clinical Trials

paper · doi:10.48550/arxiv.2106.01939

openalex publication_date 2021/06/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

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.

Citations

• The central role of the propensity score in observational studies for causal effects
• Fast Graph Representation Learning with PyTorch Geometric
• Estimating the effects of non-pharmaceutical interventions on COVID-19 in Europe
• An Introduction to Proximal Causal Learning
• Invariant Representation Learning for Treatment Effect Estimation

Cited by

• Leveraging semantic similarity for experimentation with AI-generated treatments
• Agentic Personalisation of Cross-Channel Marketing Experiences

Related

• Distilling interpretable causal trees from causal forests
• Partial Identification of Treatment Effects with Implicit Generative Models
• Neural Networks with Causal Graph Constraints: A New Approach for Treatment Effects Estimation
• Learning Representations of Instruments for Partial Identification of Treatment Effects
• Causality and Generalizability: Identifiability and Learning Methods