The dynamics of temporal networks lie in the continuous interactions between nodes, which exhibit the dynamic node preferences with time elapsing. The challenges of mining temporal networks are thus two-fold: the dynamic structure of networks and the dynamic node preferences. In this paper, we investigate the dynamic graph sampling problem, aiming to capture the preference structure of nodes dynamically in cooperation with GNNs. Our proposed Dynamic Preference Structure (DPS) framework consists of two stages: structure sampling and graph fusion. In the first stage, two parameterized samplers are designed to learn the preference structure adaptively with network reconstruction tasks. In the second stage, an additional attention layer is designed to fuse two sampled temporal subgraphs of a node, generating temporal node embeddings for downstream tasks. Experimental results on many real-life temporal networks show that our DPS outperforms several state-of-the-art methods substantially owing to learning an adaptive preference structure. The code will be released soon at https://github.com/doujiang-zheng/Dynamic-Preference-Structure.

翻译：时间网络的动态在于节点之间的连续互动,这些节点展示了动态节点偏好和时间拉动。因此,采矿时间网络的挑战有两个方面:网络的动态结构和动态节点偏好。在本文件中,我们调查动态图表抽样问题,目的是与GNNs合作动态地捕捉节点的偏好结构。我们提议的动态首选结构框架由两个阶段组成:结构抽样和图形聚合。在第一阶段,两个参数化的采样器的设计是要学习适应网络重建任务的优先结构。在第二阶段,一个额外注意层的设计是结合节点的两个抽样时间子图,为下游任务生成时间节点嵌入。许多实际时间网络的实验结果显示,由于学习了适应性偏好结构,我们的DPS大大超越了几个状态方法。代码不久将在 http://github.com/dougiang-zheng/Dynami-Preference-Structurgeretre发布。