A Mutually Exciting Latent Space Hawkes Process Model for Continuous-time Networks
A Mutually Exciting Latent Space Hawkes Process Model for Continuous-time Networks
复制标题
DOI：
10.48550/arxiv.2205.09263
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
Zhipeng Huang;Hadeel Soliman;Subhadeep Paul;Kevin S. Xu
中科院分区：
文献类型：
--
作者：
Zhipeng Huang;Hadeel Soliman;Subhadeep Paul;Kevin S. Xu
网络和时间点过程是为各种领域的复杂动态关系数据建模的基本构建块。我们提出了一种新的基于节点潜在空间表示的关系事件连续网络生成模型——潜在空间霍克斯模型。我们使用相互激励的Hawkes过程对节点之间的关系事件进行建模，其基线强度取决于潜在空间中节点之间的距离以及发送者和接收者的特定效应。我们证明，我们提出的LSH模型可以复制在真实时间网络中观察到的许多特征，包括互易性和传递性，同时也实现了比现有模型更高的预测精度，并提供了更多的可解释拟合。
Networks and temporal point processes serve as fundamental building blocks for modeling complex dynamic relational data in various domains. We propose the latent space Hawkes (LSH) model, a novel generative model for continuous-time networks of relational events, using a latent space representation for nodes. We model relational events between nodes using mutually exciting Hawkes processes with baseline intensities dependent upon the distances between the nodes in the latent space and sender and receiver specific effects. We demonstrate that our proposed LSH model can replicate many features observed in real temporal networks including reciprocity and transitivity, while also achieving superior prediction accuracy and providing more interpretable fits than existing models.