Recently, there has been a surge of interest in learning representation of graph-structured data that are dynamically evolving. However, current dynamic graph learning methods lack a principled way in modeling temporal, multi-relational, and concurrent interactions between nodes---a limitation that is especially problematic for the task of temporal knowledge graph reasoning, where the goal is to predict unseen entity relationships (i.e., events) over time. Here we present Recurrent Event Network (\method)---an architecture for modeling complex event sequences---which consists of a recurrent event encoder and a neighborhood aggregator. The event encoder employs a RNN to capture (subject, relation)-specific patterns from historical entity interactions; while the neighborhood aggregator summarizes concurrent interactions within each time stamp. An output layer is designed for predicting forthcoming, multi-relational events. Experiments on temporal link prediction over two knowledge graph datasets demonstrate the effectiveness of our method, especially on multi-step inference over time.
翻译:最近,人们开始对正在动态演变的图表结构数据的学习表现感兴趣。然而,当前动态图表学习方法在模拟时间、多关系和节点 -- -- 一个对时间知识图表推理任务特别有问题的限制之间同时互动方面缺乏原则性的方法,这种限制的目的是预测不可见的实体关系(即事件)随时间推移而变化。我们在这里介绍了经常性事件网络(method)-一个用于模拟复杂事件序列的架构 -- -- 由经常性事件编码器和邻里聚合器组成。事件编码器使用一个RNN从历史实体互动中捕捉(主题、关系)特定模式;而邻里聚合器则在每次时间标记中总结并行互动。一个产出层旨在预测即将发生的多关系事件。两个知识图形数据集的时际联系预测实验显示了我们的方法的有效性,特别是在多步骤的参考方面。