arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1803.04051cs.LGstat.ML
收藏

动态图上的表示学习

Representation Learning over Dynamic Graphs

Georgia Institute of Technology(佐治亚理工学院)

Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, Hongyuan Zha

摘要:

我们如何有效地将动态图上不断变化的信息编码为低维表示?在本文中,我们提出了DyRep,这是一个归纳式深度表示学习框架,它学习一组函数,以有效地生成随时间推移而演变的低维节点嵌入。学习的嵌入驱动两个关键过程的动态,即动态图中节点之间的通信和关联。这些过程表现出复杂的非线性动力学,在不同的时间尺度上发展,随后有助于更新节点嵌入。我们采用一个时间尺度依赖的多变量点过程模型来捕捉这些动态。我们设计了一个有效的无监督学习过程,并证明我们的方法显着优于两个现实世界的数据集的动态链接预测和事件时间预测的问题的代表性基线。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑