arXiv cs.AI· Patrick Bl\"obaum, Krishnakumar Balasubramanian, Shiva Prasad Kasiviswanathan·· 4 小时前AI 评分38
FoundCause:从观测数据中发现潜在混杂因素的因果发现基础模型
FoundCause: A Foundation Model for Causal Discovery with Latent Confounders from Observational Data
AI 导读
FoundCause 是一个仅用合成结构因果模型训练的摊销式因果发现基础模型,单次前向传播即可将数据集映射为因果图。其置换等变 Transformer 交替对样本和变量做注意力,边解码器分离边的存在与方向,可学习潜在 token 预测共享隐藏共同原因的变量对。
正文 · 原文
Abstract:Causal discovery from observational data requires recovering directed relations and latent confounding without interventions. We propose FoundCause, an {\em amortized causal discovery foundation model} trained only on synthetic structural causal models that maps datasets to causal graphs in a single forward pass. A permutation-equivariant transformer alternates attention over samples and variables to model cross-variable dependence and per-variable distributions. Pairwise dependence and asymmetry statistics guide its attention, edge decoder and confounder module. The decoder separates edge existence from direction, while triangular refinement incorporates evidence from chains and colliders. Learnable latent tokens predict which variable pairs share a hidden common cause, and a masked input representation handles missing data. To our knowledge, FoundCause is the first amortized causal discovery approach for i.i.d. observational data to predict latent confounding as a separate, explicit output. On 14 real-world and semi-synthetic datasets, FoundCause leads 11 classical and 7 amortized baselines in average AUROC, $F_1$, skeleton $F_1$, and normalized structural Hamming distance ($\mathrm{SHD}/d$): clearly in $\mathrm{SHD}/d$ ($0.875$ vs.\ $0.956$), narrowly in $F_1$ ($0.531$ vs.\ $0.516$). It also has the highest accuracy among amortized methods on bivariate cause--effect pairs.
| Comments: | Download the model at this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Methodology (stat.ME); Machine Learning (stat.ML) |
| Cite as: | arXiv:2606.17516 [cs.LG] |
| (or arXiv:2606.17516v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2606.17516 arXiv-issued DOI via DataCite |
Submission history
From: Krishnakumar Balasubramanian [view email]
[v1]
Tue, 16 Jun 2026 04:50:01 UTC (83 KB)
[v2]
Tue, 17 Nov 2026 00:07:04 UTC (99 KB)
来源:arXiv cs.AI · arxiv.org