Event prediction is a vital and challenging task in temporal knowledge graphs (TKGs), which have played crucial roles in various applications. Recently, many graph neural networks based approaches are proposed to model the graph structure information in TKGs. However, these approaches only construct graphs based on quadruplets and model the pairwise correlation between entities, which fail to capture the high-order correlations among entities. To this end, we propose DHyper, a recurrent Dual Hypergraph neural network for event prediction in TKGs, which simultaneously models the influences of the high-order correlations among both entities and relations. Specifically, a dual hypergraph learning module is proposed to discover the high-order correlations among entities and among relations in a parameterized way. A dual hypergraph message passing network is introduced to perform the information aggregation and representation fusion on the entity hypergraph and the relation hypergraph. Extensive experiments on six real-world datasets demonstrate that DHyper achieves the state-of-the-art performances, outperforming the best baseline by an average of 13.09%, 4.26%, 17.60%, and 18.03% in MRR, Hits@1, Hits@3, and Hits@10, respectively.

事件预测是时间知识图（TKG）中一项至关重要且具有挑战性的任务，它在各种应用中发挥着至关重要的作用。最近，提出了许多基于图神经网络的方法来对 TKG 中的图结构信息进行建模。然而，这些方法仅基于四元组构建图并对实体之间的成对相关性进行建模，无法捕获实体之间的高阶相关性。为此，我们提出了 DHyper，一种用于 TKG 中事件预测的循环双超图神经网络，它同时对实体和关系之间的高阶相关性的影响进行建模。具体来说，提出了一种对偶超图学习模块，以参数化的方式发现实体之间和关系之间的高阶相关性。引入双超图消息传递网络对实体超图和关系超图进行信息聚合和表示融合。对六个真实世界数据集的大量实验表明，DHyper 实现了最先进的性能，在 MRR、Hits@1、Hits 方面平均优于最佳基线 13.09%、4.26%、17.60% 和 18.03%分别为@3 和Hits@10。