用上下文学习自动估算因果效应，无需调参
CausalPFN: Amortized Causal Effect Estimation via In-Context Learning
- 基于模拟数据训练的Transformer模型，直接从观测数据输出因果效应
- 在IHDP、Lalonde等基准上平均表现优于现有方法
- 支持校准不确定性估计，适合政策决策等真实场景
从观察数据中进行因果效应估计在诸多应用中至关重要。然而，从数十种专用方法中选择合适估计算法需大量人工和领域知识。我们提出CausalPFN，一个单一Transformer模型，可一次性摊销该工作流程：在满足忽略性假设的大规模模拟数据生成过程上训练一次后，即可对新观测数据集直接推断因果效应。CausalPFN结合贝叶斯因果推断与先验拟合网络（PFN）的大规模训练范式，无需任务特定调整，直接将原始观测映射为因果效应。该方法在异质处理效应和平均处理效应估计基准（IHDP、Lalonde、ACIC）上取得更优平均性能，且在真实世界提升建模任务中表现竞争力。CausalPFN提供校准的不确定性估计，支持基于贝叶斯原则的可靠决策。此即用模型无需进一步训练或调优，推动自动化因果推断发展（https://github.com/vdblm/CausalPFN/）。
原文摘要 · Abstract (English)
Causal effect estimation from observational data is fundamental across various applications. However, selecting an appropriate estimator from dozens of specialized methods demands substantial manual effort and domain expertise. We present CausalPFN, a single transformer that amortizes this workflow: trained once on a large library of simulated data-generating processes that satisfy ignorability, it infers causal effects for new observational datasets out of the box. CausalPFN combines ideas from Bayesian causal inference with the large-scale training protocol of prior-fitted networks (PFNs), learning to map raw observations directly to causal effects without any task-specific adjustment. Our approach achieves superior average performance on heterogeneous and average treatment effect estimation benchmarks (IHDP, Lalonde, ACIC). Moreover, it shows competitive performance for real-world policy making on uplift modeling tasks. CausalPFN provides calibrated uncertainty estimates to support reliable decision-making based on Bayesian principles. This ready-to-use model requires no further training or tuning and takes a step toward automated causal inference (https://github.com/vdblm/CausalPFN/).
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。