Temporal Adaptive Convolutional Intervention Network for Counterfactual Estimation: A Domain Generalization Perspective

Xin Wang, Chi Luo, Shengfei Lyu, Xingjian Lin, Huanhuan Chen

Keywords: causal inference, longitudinal data, time-varying confounding bias, domain generalization

TL;DR: TACIN, a novel model, captures temporal treatment interactions using an Intervention-aware Functional Convolution kernel and addresses confounding bias in observational data from a domain generalization perspective.

Abstract: Accurate estimation of time-varying treatment effects is crucial for optimizing interventions in personalized medicine. However, observational data often contains complex confounding bias and temporal complexities, making counterfactual estimation challenging. We propose Temporal Adaptive Convolutional Intervention Network (TACIN), a novel model that introduces an Intervention-aware Functional Convolution kernel to emphasize the role of treatments and capture complex temporal treatment interactions. TACIN addresses confounding bias from a domain generalization perspective, approximating the unknown target domain using adversarial examples and incorporating Sharpness-Aware Minimization to derive a generalization bound. This approach is more suitable for longitudinal settings compared to existing methods inspired by domain adaptation techniques due to inherent differences between static and longitudinal contexts. Experiments on simulated datasets demonstrate TACIN's superior performance compared to state-of-the-art models for counterfactual estimation over time.

Primary Area: causal reasoning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1698