arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2110.05018cs.LGeess.SP
收藏

结构化时间先验下的时变图学习

Time-varying Graph Learning Under Structured Temporal Priors

Southeast University(东南大学)

Xiang Zhang, Qiao Wang

摘要:

本文试图通过使用结构化的时间先验知识来学习时变图,该先验知识假设图序列中任意两个图之间的潜在关系。不同于现有的基于链结构的方法中的先验知识,如时间同质性只能描述两个连续图的变化,我们提出了一个结构命名为\emph{temporal graph}来描述底层的真实时间关系。在这个框架下,链结构实际上是我们的时态图的一个特例。我们进一步提出了一种分布式算法--交替方向乘子法(ADMM)来求解诱导优化问题。数值实验证明了该方法的优越性。

英文摘要:

This paper endeavors to learn time-varying graphs by using structured temporal priors that assume underlying relations between arbitrary two graphs in the graph sequence. Different from many existing chain structure based methods in which the priors like temporal homogeneity can only describe the variations of two consecutive graphs, we propose a structure named \emph{temporal graph} to characterize the underlying real temporal relations. Under this framework, the chain structure is actually a special case of our temporal graph. We further proposed Alternating Direction Method of Multipliers (ADMM), a distributed algorithm, to solve the induced optimization problem. Numerical experiments demonstrate the superiorities of our method.

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。

↑