Invariant Graph Learning for Treatment Effect Estimation from Networked Observational Data

Yongduo Sui, Caizhi Tang, Zhixuan Chu, Junfeng Fang, Yuan Gao, Qing Cui, Longfei Li, JUN ZHOU, Xiang Wang

Keywords: Networked Data, Spillover Effect, Invariant Learning

Abstract: Treatment effect estimation from networked observational data encounters notable challenges, primarily hidden confounders arising from network structure, or spillover effects that influence unit's outcomes based on neighboring treatment assignments. Existing graph neural network (GNN)-based methods have endeavored to address these challenges, utilizing the GNN's message-passing mechanism to capture hidden confounders or model spillover effects. However, they mainly focus on transductive treatment effect learning on a single networked data, limiting their efficacy in inductive settings for real-world applications where networked data often originates from multiple environments influenced by potentially varying time or geographical regions. In light of this, we introduce the principle of invariance to the task of treatment effect estimation on networked data, culminating in our Invariant Graph Learning (IGL) framework. Specifically, it first generates multiple networked data to simulate diverse environments from a given observational data. Then it further encourages the model to learn environment-invariant representations for confounders and spillover effects. Such a design enables the model to extrapolate beyond a single observed environment, thereby improving the performance of treatment effect estimation in potential new environments. Upon extensive experiments on two real-world datasets, our IGL model demonstrates superior performance compared to state-of-the-art methods.

Track: Social Networks, Social Media, and Society

Submission Guidelines Scope: Yes

Submission Guidelines Blind: Yes

Submission Guidelines Format: Yes

Submission Guidelines Limit: Yes

Submission Guidelines Authorship: Yes

Student Author: Yes

Submission Number: 1382