Synergizing Deconfounding and Temporal Generalization For Time-series Counterfactual Outcome Estimation

TL;DR

This paper introduces a novel framework combining Sub-treatment Group Alignment and Random Temporal Masking to improve counterfactual outcome estimation from time-series data, addressing confounding and temporal generalization challenges.

Contribution

The paper proposes a new synergistic approach that integrates fine-grained treatment group alignment with temporal masking, advancing counterfactual estimation methods.

Findings

SGA improves deconfounding by aligning sub-treatment groups.

RTM enhances temporal generalization by noise-based regularization.

Combined SGA and RTM achieve state-of-the-art results.

Abstract

Estimating counterfactual outcomes from time-series observations is crucial for effective decision-making, e.g. when to administer a life-saving treatment, yet remains significantly challenging because (i) the counterfactual trajectory is never observed and (ii) confounders evolve with time and distort estimation at every step. To address these challenges, we propose a novel framework that synergistically integrates two complementary approaches: Sub-treatment Group Alignment (SGA) and Random Temporal Masking (RTM). Instead of the coarse practice of aligning marginal distributions of the treatments in latent space, SGA uses iterative treatment-agnostic clustering to identify fine-grained sub-treatment groups. Aligning these fine-grained groups achieves improved distributional matching, thus leading to more effective deconfounding. We theoretically demonstrate that SGA optimizes a tighter upper bound on counterfactual risk and empirically verify its deconfounding efficacy. RTM promotes temporal generalization by randomly replacing input covariates with Gaussian noises during training. This encourages the model to rely less on potentially noisy or spuriously correlated covariates at the current step and more on stable historical patterns, thereby improving its ability to generalize across time and better preserve underlying causal relationships. Our experiments demonstrate that while applying SGA and RTM individually improves counterfactual outcome estimation, their synergistic combination consistently achieves state-of-the-art performance. This success comes from their distinct yet complementary roles: RTM enhances temporal generalization and robustness across time steps, while SGA improves deconfounding at each specific time point.