{"type":"ScholarlyArticle","title":"Counterfactual Estimation via Temporal-Aware Intervention Networks","authors":[{"name":"Xin Wang","slug":"xin-wang","given":"Xin","family":"Wang","affiliation":""},{"name":"Chi Luo","slug":"chi-luo","given":"Chi","family":"Luo","affiliation":""},{"name":"Shengfei Lyu","slug":"shengfei-lyu","given":"Shengfei","family":"Lyu","affiliation":""},{"name":"Yi Wan","slug":"yi-wan","given":"Yi","family":"Wan","affiliation":""},{"name":"Xiren Zhou","slug":"xiren-zhou","given":"Xiren","family":"Zhou","affiliation":""},{"name":"Xiangyu Wang","slug":"xiangyu-wang","given":"Xiangyu","family":"Wang","affiliation":""},{"name":"Huanhuan Chen","slug":"huanhuan-chen","given":"Huanhuan","family":"Chen","affiliation":""}],"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 Counterfactual Estimation via Temporal-Aware Intervention Networks (TAIN), a novel model that introduces an Intervention-aware Functional Convolution kernel to emphasize the role of treatments and capture complex temporal treatment interactions. TAIN 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 TAIN's superior performance compared to state-of-the-art models for counterfactual estimation over time.","doi":"10.24963/ijcai.2026/454","url":"https://ijcai.org/proceedings/2026/454","pdf":"https://ijcai.org/proceedings/2026/0454.pdf","markdown":"https://ijcai.org/proceedings/2026/454.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/454","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Knowledge Representation and Reasoning","track":"Main Track","number":454,"pages":{"first":4079,"last":4087},"keywords":["Machine Learning: Causality","Knowledge Representation and Reasoning: Causality","Uncertainty in AI: Causality, structural causal models and causal inference"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}