Abstract
Real-world systems are made of interacting entities that evolve with time. Creating models that can forecast interactions by learning the dynamics of entities is an important problem in numerous fields. Earlier works used dynamic graph models to achieve this. However, real-world interactions are more complex than pairwise, as they involve more than two entities, and many of these higher-order interactions have directional components. Examples of these can be seen in communication networks such as email exchanges that involve a sender, and multiple recipients, citation networks, where authors draw upon the work of others, and so on. In this paper, we solve the problem of higher-order directed interaction forecasting by proposing a deep neural network-based model \textit{Directed HyperNode Temporal Point Process} for directed hyperedge event forecasting, as hyperedge provides native framework for modeling relationships among the variable number of nodes. Our proposed technique reduces the search space of possible candidate hyperedges by first forecasting the nodes at which events will be observed, based on which it generates candidate hyperedges. To demonstrate the efficiency of our model, we curated four datasets and conducted an extensive empirical study. We believe that this is the first work that solves the problem of forecasting higher-order directional interactions.
Abstract (translated)
实际系统是由相互作用的实体随着时间演化组成的。通过学习实体的动态特性来预测相互作用是许多领域的一个重要问题。早期工作使用了动态图模型来实现这一点。然而,实际相互作用比 pairwise 更加复杂,因为它们涉及更多的实体,而这些更高级别的相互作用往往具有方向性组成部分。例如,通信网络(例如包含一个发送者、多个接收者、引用网络等)可以提供这些相互作用的本地建模框架。在我们的研究中,我们提出了一个深度神经网络基模型 extit{Directed HyperNode Temporal Point Process},用于预测方向性的超节点事件预测,因为超节点提供了本地建模框架来建模可变节点之间的关系。我们提出的技术通过预测节点将观察到的事件的位置,从而生成可能的超节点候选者。为了证明我们的模型的效率,我们审查了四个数据集并进行了广泛的实证研究。我们相信这是解决预测更高级别方向性相互作用问题的第一篇论文。
URL
https://arxiv.org/abs/2301.12210
