Inferring Causal Effects Under Heterogeneous Peer Influence

Causal inference in networks should account for interference, which occurs when a unit's outcome is influenced by treatments or outcomes of peers. There can be heterogeneous peer influence between units when a unit's outcome is subjected to variable influence from different peers based on their attributes and relationships, or when each unit has a different susceptibility to peer influence. Existing solutions to causal inference under interference consider either homogeneous influence from peers or specific heterogeneous influence mechanisms (e.g., based on local neighborhood structure). This paper presents a methodology for estimating individual causal effects in the presence of heterogeneous peer influence due to arbitrary mechanisms. We propose a structural causal model for networks that can capture arbitrary assumptions about network structure, interference conditions, and causal dependence. We identify potential heterogeneous contexts using the causal model and propose a novel graph neural network-based estimator to estimate individual causal effects. We show that existing state-of-the-art methods for individual causal effect estimation produce biased results in the presence of heterogeneous peer influence, and that our proposed estimator is robust.