This paper proposes a novel model for predicting subgraphs in dynamic graphs, an extension of traditional link prediction. This proposed end-to-end model learns a mapping from the subgraph structures in the current snapshot to the subgraph structures in the next snapshot directly, i.e., edge existence among multiple nodes in the subgraph. A new mechanism named cross-attention with a twin-tower module is designed to integrate node attribute information and topology information collaboratively for learning subgraph evolution. We compare our model with several state-of-the-art methods for subgraph prediction and subgraph pattern prediction in multiple real-world homogeneous and heterogeneous dynamic graphs, respectively. Experimental results demonstrate that our model outperforms other models in these two tasks, with a gain increase from 5.02% to 10.88%.

翻译：本文提出了一个用于预测动态图中子图的新型模型,这是传统链接预测的延伸。 这个提议的端到端模型直接从当前快照中的子图结构到下一个快照中的子图结构,即子图中多个节点之间的边缘存在。一个称为双向模块的交叉注意的新机制旨在将节点属性信息和地形信息结合起来,以学习子图的演变。我们比较了我们的模型和多个真实世界的同质和多元动态图中分别用于子图预测和子图示模式预测的几种最先进的方法。实验结果表明,我们的模型在这两项任务中比其他模型成功,从5.02%增加到10.88%。