arXiv：cs.AI· Yiqi Su, Rashed Shelim, Lingyi Wang, Walid Saad, Naren Ramakrishnan·· 13 小时前
EpiMind：面向受限流行病政策规划的图世界模型
Graph World Models for Constrained Epidemic Policy Planning
AI 导读
研究者提出 EpiMind，一个面向跨区域受限流行病政策规划的图世界模型框架，由 graph-factored 循环状态空间模型生成联合政策条件下的推演，并用 graph-temporal ADMM 优化区域干预、通过投影保证共享资源可行性。
正文
Abstract:Epidemic policy planning often requires coordination between geographical regions, taking into account mobility-driven spillovers and how to make use of limited resources. Existing methods either lack action-conditioned models of coupled dynamics or cannot guarantee per-period feasibility. We present EpiMind, a graph world model framework for constrained epidemic policy planning across regions. A graph-factored recurrent state-space model generates joint policy-conditioned rollouts from regional latent beliefs, while graph-temporal ADMM optimizes regional interventions, enforces shared-resource feasibility through projection, and evaluates temporal specifications under the learned model. EpiMind reduces admission RMSE by 29% relative to graph-free dynamics modeling, plans within 1-5% of the best feasible constant policy with guaranteed shared-budget feasibility, and outperforms all deployable baselines across three resource budgets in real-context evaluation. These results demonstrate that graph-structured policy imagination with explicit constrained coordination supports effective epidemic interventions from learned dynamics.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.35545 [cs.LG] |
| (or arXiv:2609.35545v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.35545 arXiv-issued DOI via DataCite |
Submission history
From: Yiqi Su [view email]
[v1]
Mon, 28 Sep 2026 16:22:49 UTC (4,375 KB)
[v2]
Fri, 9 Oct 2026 03:29:07 UTC (4,375 KB)
来源：arXiv：cs.AI · arxiv.org