分布漂移下连续时间动态图的不变图表示
Invariant Graph Representations for Continuous-Time Dynamic Graphs Under Distribution Shifts
AI总结:
针对连续时间动态图在分布外场景下鲁棒性不足的问题,提出基于结构因果模型ICCM的框架CIR,利用归一化加权几何平均近似干预预测,通过子图提取器和环境记忆库捕获不变模式,实验表明其优于现有方法。
摘要:
连续时间动态图(CTDG)能够对演化关系系统进行细粒度建模。然而,现有的大多数CTDG表示学习方法适用于分布内设置,在分布外(OOD)漂移下鲁棒性有限。尽管最近的因果方法通过干预学习不变表示,但它们主要针对静态或离散时间图设计,并且由于结构和时间变化的组合爆炸,对于CTDG在计算上变得难以承受。为了解决这些挑战,我们提出了CIR,一个基于称为ICCM的新型结构因果模型的框架。为了避免穷举干预,我们利用归一化加权几何平均(NWGM)来有效近似干预预测。我们进一步在实用的深度学习架构中实例化ICCM,该架构通过专用的子图提取器联合捕获不变的结构和时间模式,并维护一个环境记忆库来建模跨演化上下文的分布漂移。大量实验表明,CIR在各种OOD场景下始终优于现有方法。
英文摘要:
Continuous-Time Dynamic Graphs (CTDGs) enable fine-grained modeling of evolving relational systems. However, most existing CTDG representation learning methods are tailored to in-distribution settings and exhibit limited robustness under out-of-distribution (OOD) shifts. Although recent causal approaches learn invariant representations via interventions, they are primarily designed for static or discrete-time graphs and become computationally prohibitive for CTDGs due to the combinatorial explosion of structural and temporal variations. To address these challenges, we propose CIR, a framework grounded in a novel structural causal model termed the ICCM. To avoid exhaustive interventions, we leverage the Normalized Weighted Geometric Mean (NWGM) to efficiently approximate interventional predictions. We further instantiate ICCM within a practical deep learning architecture that jointly captures invariant structural and temporal patterns through dedicated subgraph extractors, and maintains an environment memory bank to model distributional shifts across evolving contexts. Extensive experiments demonstrate that CIR consistently outperforms existing methods under diverse OOD scenarios.
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。