从时间网络中学习动态偏好结构的嵌入

时间网络的动态在于节点之间的连续交互作用，随着时间的推移，节点表现出动态的节点偏好。因此，挖掘时间网络的挑战有两方面：网络的动态结构和动态节点偏好。本文研究了动态图采样问题，目的是与gnn协同动态捕获节点的偏好结构。我们提出的动态偏好结构(DPS)框架包括两个阶段：结构采样和图融合。在第一阶段，设计了两个参数化的采样器，通过网络重构任务自适应地学习偏好结构。在第二阶段，设计了一个额外的注意层来融合一个节点的两个采样的时间子图，生成针对下游任务的时间节点嵌入。在许多真实时间网络上的实验结果表明，由于学习了一种自适应偏好结构，我们的DPS的性能实质上优于几种最先进的方法。该代码将很快在这个httpsURL上发布。

原文题目：Learning Dynamic Preference Structure Embedding From Temporal Networks

原文：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 this https URL.