Estimating Treatment Effects in Networks using Domain Adversarial Training
This work addresses a critical issue in causal inference for network data, where existing methods rely on unrealistic assumptions, offering a novel solution that could improve treatment effect estimation in social networks or similar domains, though it appears incremental as it builds on prior techniques like graph neural networks and domain adversarial training.
The paper tackled the problem of estimating heterogeneous treatment effects in networks, where interference and network-level covariate shift complicate accurate estimation, by proposing HINet, which integrates graph neural networks with domain adversarial training to handle unknown exposure mappings and mitigate covariate shift, achieving effective results in empirical evaluations on synthetic and semi-synthetic datasets.
Estimating heterogeneous treatment effects in network settings is complicated by interference, meaning that the outcome of an instance can be influenced by the treatment status of others. Existing causal machine learning approaches usually assume a known exposure mapping that summarizes how the outcome of a given instance is influenced by others' treatment, a simplification that is often unrealistic. Furthermore, the interaction between homophily -- the tendency of similar instances to connect -- and the treatment assignment mechanism can induce a network-level covariate shift that may lead to inaccurate treatment effect estimates, a phenomenon that has not yet been explicitly studied. To address these challenges, we propose HINet, a novel method that integrates graph neural networks with domain adversarial training. This combination allows estimating treatment effects under unknown exposure mappings while mitigating the impact of (network-level) covariate shift. An extensive empirical evaluation on synthetic and semi-synthetic network datasets demonstrates the effectiveness of our approach.