Networks representation aims to encode vertices into a low-dimensional space, while preserving the original network structures and properties. Most existing methods focus on static network structure without considering temporal dynamics. However, in real world, most networks (e.g., social and biological networks) are dynamic in nature and are constantly evolving over time. Such temporal dynamics are critical in representations learning, especially for predicting dynamic networks behaviors. To this end, a Deep Hawkes Process based Dynamic Networks Representation algorithm (DHPrep) is proposed in this paper, which is capable of capturing temporal dynamics of dynamic networks. Specifically, DHPrep incorporates both structural information and temporal dynamics to learn vertices representations that can model the edge formation process for a vertex pair, where the structural information is used to capture the historical impact from their neighborhood, and the temporal dynamics utilize this historical information and apply Hawkes point process to model the edges formation process. Moreover, a temporal smoother is further imposed to ensure the representations evolve smoothly over time. To evaluate the effectiveness of DHPrep, extensive experiments are carried out using four real-world datasets. Experimental results reveal that our DHPrep algorithm outperforms state-of-the-art baseline methods in various tasks including link prediction and vertices recommendation.

翻译：网络表示旨在将节点编码到低维空间，同时保持原始网络的结构与特性。现有方法大多关注静态网络结构，未考虑时序动态性。然而在现实世界中，绝大多数网络（如社交网络与生物网络）本质上是动态的，并随时间持续演化。此类时序动态性在表示学习中至关重要，尤其对于预测动态网络行为。为此，本文提出一种基于深度霍克斯过程的动态网络表示算法（DHPrep），该算法能够捕捉动态网络的时序动态特征。具体而言，DHPrep融合结构信息与时序动态性来学习节点表示，从而建模顶点对之间的连边形成过程：其中结构信息用于捕捉来自邻域的历史影响，时序动态性则利用该历史信息并应用霍克斯点过程来建模连边形成过程。此外，算法进一步引入时序平滑器以确保表示随时间平滑演化。为评估DHPrep的有效性，我们在四个真实数据集上进行了大量实验。实验结果表明，在链接预测与节点推荐等多项任务中，DHPrep算法均优于当前最先进的基线方法。