基于因果图的生成模型，能预测干预与反事实场景下的时间序列变化。
DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Series
- 在因果有向无环图上构建流模型，实现观测、干预和反事实预测统一建模。
- 在合成数据和水电、癌症治疗真实数据上均实现精准预测与异常检测。
- 适合需要因果推理的复杂系统建模，如医疗、能源等多变量动态系统。
时间序列预测日益需要不仅准确的观测预测，还需在多变量系统中对干预和反事实查询进行因果预测。我们提出DoFlow，一种基于因果有向无环图（DAG）的流生成模型，通过连续归一化流（CNF）的自然编码-解码机制，实现一致的观测、干预和反事实预测。同时，在一定假设下提供反事实恢复理论支持。除预测外，DoFlow还给出未来轨迹的显式似然，支持严谨的异常检测。在具有不同因果结构的合成数据及真实世界的水电和癌症治疗时间序列上实验表明，DoFlow实现了系统级观测预测的高精度，支持干预与反事实查询的因果预测，并有效检测异常。本工作推动了因果推理与生成建模在复杂动力系统中的融合。
原文摘要 · Abstract (English)
Time-series forecasting increasingly demands not only accurate observational predictions but also causal forecasting under interventional and counterfactual queries in multivariate systems. We present DoFlow, a flow-based generative model defined over a causal Directed Acyclic Graph (DAG) that delivers coherent observational and interventional predictions, as well as counterfactuals through the natural encoding-decoding mechanism of continuous normalizing flows (CNFs). We also provide a supporting counterfactual recovery theory under certain assumptions. Beyond forecasting, DoFlow provides explicit likelihoods of future trajectories, enabling principled anomaly detection. Experiments on synthetic datasets with various causal DAG structures and real-world hydropower and cancer-treatment time series show that DoFlow achieves accurate system-wide observational forecasting, enables causal forecasting over interventional and counterfactual queries, and effectively detects anomalies. This work contributes to the broader goal of unifying causal reasoning and generative modeling for complex dynamical systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。