Dynamic systems that consist of a set of interacting elements can be abstracted as temporal networks. Recently, higher-order patterns that involve multiple interacting nodes have been found crucial to indicate domain-specific laws of different temporal networks. This posts us the challenge of designing more sophisticated hypergraph models for these higher-order patterns and the associated new learning algorithms. Here, we propose the first model, named HIT, for higher-order pattern prediction in temporal hypergraphs. Particularly, we focus on predicting three types of common but important interaction patterns involving three interacting elements in temporal networks, which could be extended to even higher-order patterns. HIT extracts the structural representation of a node triplet of interest on the temporal hypergraph and uses it to tell what type of, when, and why the interaction expansion could happen in this triplet. HIT could achieve significant improvement(averaged 20% AUC gain to identify the interaction type, uniformly more accurate time estimation) compared to both heuristic and other neural-network-based baselines on 5 real-world large temporal hypergraphs. Moreover, HIT provides a certain degree of interpretability by identifying the most discriminatory structural features on the temporal hypergraphs for predicting different higher-order patterns.

中文翻译：

---

时间网络中的神经高阶模式（Motif）预测

由一组交互元素组成的动态系统可以抽象为时间网络。最近，已经发现涉及多个交互节点的高阶模式对于指示不同时间网络的特定领域定律至关重要。这给我们带来了为这些高阶模式和相关的新学习算法设计更复杂的超图模型的挑战。在这里，我们提出了第一个名为 HIT 的模型，用于时间超图中的高阶模式预测。特别是，我们专注于预测涉及时间网络中三个交互元素的三种常见但重要的交互模式，这些模式可以扩展到更高阶的模式。HIT 提取时间超图上感兴趣的节点三元组的结构表示，并使用它来说明该三元组中可能发生交互扩展的类型、时间和原因。与启发式和其他基于神经网络的基线在 5 个真实世界的大型时间超图中相比，HIT 可以实现显着改进（平均 20% AUC 增益以识别交互类型，统一更准确的时间估计）。此外，HIT 通过识别时间超图上最具辨别力的结构特征来预测不同的高阶模式，提供了一定程度的可解释性。与启发式和其他基于神经网络的基线在 5 个真实世界的大型时间超图中相比，统一更准确的时间估计。此外，HIT 通过识别时间超图上最具辨别力的结构特征来预测不同的高阶模式，提供了一定程度的可解释性。与启发式和其他基于神经网络的基线在 5 个真实世界的大型时间超图中相比，统一更准确的时间估计。此外，HIT 通过识别时间超图上最具辨别力的结构特征来预测不同的高阶模式，提供了一定程度的可解释性。