论文标题
重要的纽带图形神经网络，用于连续时间时间网络建模
Significant Ties Graph Neural Networks for Continuous-Time Temporal Networks Modeling
论文作者
论文摘要
时间网络适用于建模复杂发展的系统。它具有广泛的应用，例如社交网络分析，推荐系统和流行病学。最近，对这种动态系统进行建模引起了许多领域的关注。但是，大多数现有方法都求助于暂时网络的离散快照，并以同等的重要性进行建模所有事件。本文提出了显着的纽带图形神经网络（STGNN），这是一个捕获并描述重要关系的新型框架。为了更好地模拟相互作用的多样性，STGNN引入了一种新型的聚合机制，以组织最重要的历史邻居信息并自适应地获得节点对的重要性。四个真实网络的实验结果证明了所提出的框架的有效性。
Temporal networks are suitable for modeling complex evolving systems. It has a wide range of applications, such as social network analysis, recommender systems, and epidemiology. Recently, modeling such dynamic systems has drawn great attention in many domains. However, most existing approaches resort to taking discrete snapshots of the temporal networks and modeling all events with equal importance. This paper proposes Significant Ties Graph Neural Networks (STGNN), a novel framework that captures and describes significant ties. To better model the diversity of interactions, STGNN introduces a novel aggregation mechanism to organize the most significant historical neighbors' information and adaptively obtain the significance of node pairs. Experimental results on four real networks demonstrate the effectiveness of the proposed framework.
