<ul data-eligibleForWebStory="false"><li>Estimating individual-level treatment effect from observational data is a crucial task in causal inference, with applications in various domains.</li><li>A new algorithm is proposed in this work that uses disentangled representation methods to decompose observed covariates into instrumental, confounding, and adjustment factors.</li><li>The algorithm incorporates a mixture of experts with multi-head attention and a linear orthogonal regularizer to softly decompose pre-treatment variables and eliminate selection bias through importance sampling re-weighting techniques.</li><li>Extensive experiments on both public semi-synthetic and real-world datasets demonstrate that the proposed algorithm surpasses existing methods in estimating individual treatment effects.</li></ul>

Deep Disentangled Representation Network for Treatment Effect Estimation

Discover more