Orca：用于连续时间因果推理的神经算子
Orca: Neural Operators for Causal Reasoning in Continuous Time
浏览论文内容
中文总结 AI 辅助
针对需处理连续时间、不规则观测及反馈循环的系统，提出神经算子框架Orca，扩展神经算子架构表达因果机制，在合成示例上实现反事实推理。
中文摘要 AI 辅助
结构因果模型是推理干预和反事实的标准语言，但它们描述的是静态变量，通常仅测量一次，且通常禁止循环依赖。我们关注的许多系统，如患者、气候和经济，反而随时间连续演化，在不规则时间点被观测，且包含反馈循环。我们认为神经算子学习为此类场景下的因果推理提供了自然基础，并提出了框架Orca，其中因果图的每个节点是时间的函数，每个机制是函数空间之间的学习映射。我们扩展现有神经算子架构以表达因果机制：机制将多个父节点函数作为输入，从父节点计算节点的函数值，遵循时间箭头，并将潜在外生噪声视为可推断并可用于反事实的函数。我们形式化了模型类，并在合成连续时间示例上展示了反事实推理，代码可在指定URL获取。
英文摘要
Structural causal models are the standard language for reasoning about interventions and counterfactuals, but they describe static variables, typically measured once, and usually forbid cyclic dependencies. Many systems we care about, such as patients, climates, and economies, instead evolve continuously in time, are observed at irregular time points, and contain feedback loops. We argue that neural operator learning provides a natural foundation for causal reasoning in this setting, and propose Orca, a framework in which each node of the causal graph is a function of time and each mechanism is a learned map between function spaces. We extend existing neural operator architectures to express causal mechanisms: a mechanism computes the function value of a node from its parent nodes by taking several parent functions as input, respects the arrow of time, and treats latent exogenous noise as a function that can be inferred and reused for counterfactuals. We formalize the model class and demonstrate counterfactual reasoning on synthetic continuous-time examples. Code is available at https://github.com/gerritgr/orca
