发表机构
University of Houston（休斯顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究旨在量化图模型中节点群体间方向性影响，提出基于图模型的结构化反事实干预框架，训练邻居影响模型并定义CDS，通过实验验证该方法能有效恢复方向性影响，对混杂信号有鲁棒性，在生物数据上有合理一致的相互作用。
AI 中文摘要
在基于图的建模中，量化节点群体之间的方向性影响是一个基本问题，尤其是在空间生物系统中，细胞间相互作用决定功能结果。现有基于注意力、归因或相关性的方法只能捕捉关联，无法为评估可控扰动下的方向性效应提供原则框架。我们引入一个用于基于图模型的结构化反事实干预框架，以估计节点类型之间的方向性影响。通过训练邻居影响模型预测节点状态，并应用约束干预来修改邻域组成。定义反事实方向性得分（CDS）来衡量目标扰动引起的预测节点状态变化，并给出其作为局部干预敏感性有限差分度量的理论解释。为获得有效不确定性估计，引入核心级自举程序。在具有已知方向性结构的合成空间图上的实验表明，CDS能恢复方向性影响，在零假设条件下校准良好且对混杂信号具有鲁棒性，在空间转录组学数据上的初步结果揭示了跨组织核心的生物学上合理且一致的相互作用。
英文摘要
Quantifying directional influence between node populations is a fundamental problem in graph-based modeling, particularly in spatial biological systems where cell-cell interactions shape functional outcomes. Existing approaches based on attention, attribution, or correlation capture associations but do not provide a principled framework for evaluating directional effects under controlled perturbations. We introduce a framework for structured counterfactual interventions in graph-based models to estimate directional influence between node types. Our approach trains a Neighbor Influence Model (NIM) to predict node states from local neighborhoods and applies constrained interventions that modify neighborhood composition while preserving key spatial and structural properties. We define the Counterfactual Directionality Score (CDS), which measures the change in predicted node state induced by targeted perturbations, and provide a theoretical interpretation of CDS as a finite-difference measure of local intervention sensitivity. To obtain valid uncertainty estimates, we introduce a core-level bootstrap procedure that accounts for dependencies within spatial samples. Experiments on synthetic spatial graphs with known directional structure show that CDS recovers directional influence, remains well calibrated under null conditions, and is robust to confounding signals, while preliminary results on spatial transcriptomics data reveal biologically plausible and consistent interactions across tissue cores.
Comments15 pages, 4 figures
