提出可零样本推断时间因果关系并输出可靠性信号的工业级模型
Temporal Causal Prior-Data Fitted Networks for Panel Data with Learned Reliability Signals
- 基于混合先验与跨时序注意力架构，实现时间因果建模
- 在19个数据集上零样本表现达AUROC 0.93–0.98，可靠性检测F1达0.94
- 适用于大规模工业时序数据，支持快速部署与可解释性分析
工业时间序列中的因果效应估计需应对时序动态、时变处理及未观测混杂因素。现有方法（如CausalPFN、CausalFM）仅处理静态横截面数据；神经时间方法（CRN、G-Net）需针对每项数据集训练；同时期的时序-PFN方法尚未在工业规模验证，且均不输出个体因果对的可靠性信号。本文提出时序因果先验-数据拟合网络（TCPFN），一种支持零样本时序因果发现的基础模型，具备学习可靠性信号的能力。其贡献包括：（1）因果判断头，联合预测无效应概率、混杂强度、可识别性、中介比例及因果模式；（2）覆盖六类因果机制（独立、直接、混杂、中介、时变混杂、反馈）及前门、工具变量先验的混合训练先验；（3）基于离散令牌的面板数据架构，结合交叉注意力掩码防止跨时域信息泄露；（4）通过FAISS上下文选择与一步后验修正，实现单卡6小时内对V=1,275的私有造纸数据集推理。在五个领域19个基准数据集上，TCPFN零样本表现优异：Tennessee Eastman AUROC 0.96，SWaT 0.93，Causal Rivers 0.98，CAUSRCA 0.97。空效应检测器达到NullF1 0.94，AUROC 0.99。相较之下，仅使用CPU的PCMCI在子面板（V=666）耗时81.5小时，外推至全量需约12.5天。TCPFN捕捉到跨系统因果关系，而PCMCI仅识别局部控制器-测量耦合，凸显其可扩展性优势。
原文摘要 · Abstract (English)
Estimating causal effects in industrial time series requires handling temporal dynamics, time-varying treatments, and unobserved confounders. Existing causal foundation models (CausalPFN, CausalFM) operate only on static cross-sectional data; neural temporal methods (CRN, G-Net) require per-dataset training; and concurrent temporal-PFN proposals have not been demonstrated at industrial scale. None output explicit per-pair reliability signals alongside their CATE estimates. We introduce Temporal Causal Prior-Data Fitted Networks (TCPFN), a foundation model for zero-shot temporal causal discovery with learned reliability signals. TCPFN makes four contributions: (1) a Causal Judgment Head that jointly predicts null-effect probability, confounding strength, identifiability, mediation fraction, and causal regime; (2) a mixed training prior covering six causal regimes (independent, direct, confounded, mediated, time-varying confounded, feedback) plus CausalFM-style front-door and instrumental-variable priors; (3) a discrete-token panel-data architecture with cross-attention masking that prevents inter-horizon leakage; (4) zero-shot inference at industrial scale via FAISS-based context selection and one-step posterior correction. On 19 benchmark datasets across five domains, TCPFN achieves competitive zero-shot causal discovery: AUROC 0.96 on Tennessee Eastman, 0.93 on SWaT, 0.98 on Causal Rivers, 0.97 on CAUSRCA. The null detector reaches NullF1 0.94, AUROC 0.99. TCPFN scales to V=1,275 on a proprietary Kraft pulp-and-paper dataset in 6 hours on a single GPU; PCMCI, a CPU-only library, on a V=666 sub-panel of the same data took 81.5 hours, extrapolating by O(V^2) to ~12.5 days at V=1,275. TCPFN's top edges identify cross-subsystem causal relationships while PCMCI's surface within-instrument controller-measurement coupling -- a scalability case study.
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。