arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.02161cs.LGcs.SYeess.SY
收藏

生成因果时间交互图以验证时间链接预测的反事实性

Generating Causal Temporal Interaction Graphs for Counterfactual Validation of Temporal Link Prediction

University of Oxford(牛津大学)

Aniq Ur Rahman, Justin P. Coon

AI总结:

本文提出通过生成因果时间交互图来验证时间链接预测模型的反事实性,引入结构方程模型并提出基于预测误差的距离度量,用于评估因果模型的鲁棒性。

摘要:

时间链接预测(TLP)模型通常基于预测准确性进行评估,但此类评估并未评估这些模型是否捕捉了支配时间交互的因果机制。在本工作中,我们提出了一种框架,通过生成具有已知真实因果结构的因果时间交互图(CTIGs)来验证TLP模型的反事实性。我们首先介绍了一个适用于连续时间事件序列的结构方程模型,该模型支持兴奋性和抑制性效应,然后将这种机制扩展到时间交互图中。为了比较因果模型,我们提出了一种基于跨模型预测误差的距离度量,并实证验证了假设:在足够远的模型上训练的预测器在评估时会退化。最后,我们在(i)生成模型之间的受控因果偏移和(ii)时间戳洗牌作为具有可测量因果距离的随机扭曲下实例化反事实评估。我们的框架为因果意识的基准测试提供了基础。

英文摘要:

Temporal link prediction (TLP) models are commonly evaluated based on predictive accuracy, yet such evaluations do not assess whether these models capture the causal mechanisms that govern temporal interactions. In this work, we propose a framework for counterfactual validation of TLP models by generating causal temporal interaction graphs (CTIGs) with known ground-truth causal structure. We first introduce a structural equation model for continuous-time event sequences that supports both excitatory and inhibitory effects, and then extend this mechanism to temporal interaction graphs. To compare causal models, we propose a distance metric based on cross-model predictive error, and empirically validate the hypothesis that predictors trained on one causal model degrade when evaluated on sufficiently distant models. Finally, we instantiate counterfactual evaluation under (i) controlled causal shifts between generating models and (ii) timestamp shuffling as a stochastic distortion with measurable causal distance. Our framework provides a foundation for causality-aware benchmarking.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑