动态图的测地线用于状态转换检测
Geodesics of Dynamic Graphs for Regime Change Detection
AI总结:
提出将动态网络中的状态定义为时间图沿测地线的轨迹,通过图回归方法测量观测图与测地线的累积距离,结合变点检测算法识别状态转换,在合成和真实数据上优于现有方法。
摘要:
传统动态网络中的变点检测假设平稳状态之间的突然转换,忽略了大多数实际应用(如社交网络或物理系统)中出现的连续演化场景。我们通过将状态正式定义为时间图中连贯动态的时期来弥补这一空白,并将其表征为在适当定义的图空间中沿测地线的轨迹。这一原创视角使我们能够将状态转换定义为动态中的显著漂移,要么朝向新轨迹,要么速度变化。我们利用图回归方法测量观测图序列与相关图空间中其端点之间估计测地线的累积距离,并可将其与变点检测算法结合。我们在具有变化轨迹和不同速度的动态网络上进行实验,结果优于最先进的变点检测模型。然后,我们分析了新冠疫情期间的流动性数据,并表明我们对规则网络演化的假设导致变点与外部事件相比基线方法的结果更一致。我们的工作是首次在图空间中建模和检测演化状态之间的变化,为分析复杂时间图数据提供了现实且强大的工具。
英文摘要:
Traditional change point detection in dynamic networks assumes abrupt transitions between stationary states, overlooking scenarios of continuous evolution which arise in most real-world applications, such as social networks or physical systems. We address this gap by formally defining regimes as periods of coherent dynamics in temporal graphs, which we characterize as trajectories along geodesics in a suitably defined graph space. This original perspective allows us to define regime changes as significant drifts in dynamics, either toward new trajectories or with pace changes. We leverage graph regression methods to measure the cumulative distance of sequences of observed graphs from the estimated geodesics between their endpoints, in the relevant graph space, which we can combine with change point detection algorithms. We present experiments on dynamic networks, with changing trajectories and varying speeds, in which we outperform state of the art change point detection models. Then, we analyse mobility data during the Covid-19 pandemic, and show that our assumptions on regular network evolution lead to change points that are more aligned to external events compared to the outcomes of baseline methods. Our work is the first to model and detect changes between evolving regimes in graph space, providing a realistic and powerful tool for analyzing complex temporal graph data.
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。