arXiv：cs.LG· Jennifer Wendland, Nicolas Freitag, Maik Kschischo·· 7 小时前AI 评分35
Observable Neural ODEs：面向连续时间可识别因果预测的神经网络常微分方程
Observable Neural ODEs for Identifiable Causal Forecasting in Continuous Time
AI 导读
研究者提出 Observable Neural ODEs（ObsNODEs），一种基于可观测标准型的 Neural ODE 模型，用于在连续时间下实现可识别的因果预测。
正文
Abstract:Causal inference in continuous-time sequential decision problems is challenged by hidden confounding and partially observed states. We show that, under explicit structural assumptions, observability of the latent state enables identification of dynamic treatment effects through a continuous-time conditional front-door adjustment, even in the presence of hidden confounding.
We derive a general adjustment formula and show that it reduces to a tractable state-space formula when unobserved contemporaneous disturbances are temporally uncorrelated. This formula expresses potential-outcome distributions under alternative treatment trajectories through the measurement model, latent dynamics, and the filtering distribution over latent states.
We propose Observable Neural ODEs (ObsNODEs), Neural ODE models in observable normal form that implement this tractable adjustment for causal forecasting. ObsNODEs learn continuous-time dynamics with states reconstructible from observations, enabling outcome prediction under alternative treatment paths.
Experiments on synthetic, semi-synthetic, and real-world clinical data demonstrate strong performance over recent sequence models, including external validation.
| Comments: | 20 pages, 5 figures |
| Subjects: | Machine Learning (cs.LG); Optimization and Control (math.OC); Statistics Theory (math.ST); Quantitative Methods (q-bio.QM) |
| MSC classes: | 34H99 (Primary) 37N25 37N35 (Secondary) |
| ACM classes: | I.2.6; I.2.8 |
| Cite as: | arXiv:2604.26070 [cs.LG] |
| (or arXiv:2604.26070v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.26070 arXiv-issued DOI via DataCite |
Submission history
From: Maik Kschischo [view email]
[v1]
Tue, 28 Apr 2026 19:18:42 UTC (483 KB)
[v2]
Wed, 13 May 2026 13:30:16 UTC (484 KB)
[v3]
Tue, 6 Oct 2026 10:24:43 UTC (555 KB)
来源：arXiv：cs.LG · arxiv.org