Spatial Deconfounder: Interference-Aware Deconfounding for Spatial Causal Inference

2025-10-09

AI Summary

Spatial causal inference faces dual challenges: unobserved spatial confounding (e.g., weather, pollution) and interference from neighboring units’ treatments. To address these, we propose a two-stage framework. First, we model interference as a multi-cause signal and establish its relationship with latent confounding structure, enabling nonparametric identification of both direct and spillover effects under weak assumptions—without requiring multiple treatment types or prespecified latent field models. Second, we design a conditional variational autoencoder (CVAE) incorporating spatial priors to reconstruct unobserved confounders, coupled with a flexible outcome model for causal estimation. We evaluate our method on an extended version of the SpaCE benchmark and real-world datasets from environmental health and social science. Results demonstrate consistent and significant improvements in causal effect estimation accuracy over state-of-the-art approaches.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Causal inference in spatial domains faces two intertwined challenges: (1) unmeasured spatial factors, such as weather, air pollution, or mobility, that confound treatment and outcome, and (2) interference from nearby treatments that violate standard no-interference assumptions. While existing methods typically address one by assuming away the other, we show they are deeply connected: interference reveals structure in the latent confounder. Leveraging this insight, we propose the Spatial Deconfounder, a two-stage method that reconstructs a substitute confounder from local treatment vectors using a conditional variational autoencoder (CVAE) with a spatial prior, then estimates causal effects via a flexible outcome model. We show that this approach enables nonparametric identification of both direct and spillover effects under weak assumptions--without requiring multiple treatment types or a known model of the latent field. Empirically, we extend SpaCE, a benchmark suite for spatial confounding, to include treatment interference, and show that the Spatial Deconfounder consistently improves effect estimation across real-world datasets in environmental health and social science. By turning interference into a multi-cause signal, our framework bridges spatial and deconfounding literatures to advance robust causal inference in structured data.

Problem

• Addresses unmeasured spatial factors confounding treatment and outcome
• Solves interference from nearby treatments violating no-interference assumptions
• Reconstructs substitute confounders to estimate direct and spillover effects

Innovation

• Uses conditional variational autoencoder with spatial prior
• Reconstructs substitute confounder from local treatments
• Estimates causal effects via flexible outcome model