How can we effectively encode evolving information over dynamic graphs into low-dimensional representations? In this paper, we propose DyRep, an inductive deep representation learning framework that learns a set of functions to efficiently produce low-dimensional node embeddings that evolves over time. The learned embeddings drive the dynamics of two key processes namely, communication and association between nodes in dynamic graphs. These processes exhibit complex nonlinear dynamics that evolve at different time scales and subsequently contribute to the update of node embeddings. We employ a time-scale dependent multivariate point process model to capture these dynamics. We devise an efficient unsupervised learning procedure and demonstrate that our approach significantly outperforms representative baselines on two real-world datasets for the problem of dynamic link prediction and event time prediction.

本文提出了一种基于动态图的归纳式深层表示学习框架（DyRep），能够学习一组函数以高效生成随时间演变的低维节点嵌入，这些嵌入驱动动态图中节点之间的通信与关联，并利用时间为尺度的多元点过程模型来捕获这些动态关系，该研究通过动态链接预测和事件时间预测问题的两个真实世界数据集的实验证明了框架的有效性。

动态图上的表示学习