Causal Effect Estimation under Networked Interference without Networked Unconfoundedness Assumption

2025-02-27

AI Summary

Existing methods for causal effect identification under network interference rely on the stringent no-network-confounding assumption, which is often violated in practice. Method: This paper proposes a novel causal effect estimation framework that dispenses with this assumption. It systematically distinguishes and models three types of latent confounders—those affecting ego units, their neighbors, or their interaction—and constructs a network effect estimator based on identifiable representation learning. Under a structural causal model, we rigorously establish the global identifiability of the proposed estimator. Contribution/Results: Theoretical analysis guarantees unbiased estimation of networked causal effects. Empirical evaluation on multiple synthetic and real-world network datasets demonstrates substantial improvements over state-of-the-art baselines, achieving an average 32% reduction in estimation error.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Knowledge Representation and Reasoning: Action, Change, and Causality

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Estimating causal effects under networked interference is a crucial yet challenging problem. Existing methods based on observational data mainly rely on the networked unconfoundedness assumption, which guarantees the identification of networked effects. However, the networked unconfoundedness assumption is usually violated due to the latent confounders in observational data, hindering the identification of networked effects. Interestingly, in such networked settings, interactions between units provide valuable information for recovering latent confounders. In this paper, we identify three types of latent confounders in networked inference that hinder identification: those affecting only the individual, those affecting only neighbors, and those influencing both. Specifically, we devise a networked effect estimator based on identifiable representation learning techniques. Theoretically, we establish the identifiability of all latent confounders, and leveraging the identified latent confounders, we provide the networked effect identification result. Extensive experiments validate our theoretical results and demonstrate the effectiveness of the proposed method.

Problem

• Estimating causal effects under networked interference
• Identifying latent confounders in networked settings
• Devising a networked effect estimator using representation learning

Innovation

• Causal effect estimation technique
• Identifiable representation learning method
• Latent confounders identification strategy