arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.01346cs.LGcs.SIstat.ML
收藏

基于随机游动的动态图高效表示学习

Efficient Representation Learning Using Random Walks for Dynamic Graphs

KTH Royal Institute of Technology(瑞典皇家理工学院);Data61, CSIRO(澳大利亚联邦科学与工业研究组织数据61中心)

Hooman Peiro Sajjad, Andrew Docherty, Yuriy Tyshetskiy

摘要:

图上的许多机器学习工作流的重要部分是顶点表示学习,即,学习所述图中的每个顶点的低维向量表示。最近,几个强大的技术,无监督表示学习已被证明给国家的最先进的性能在下游任务,如顶点分类和边缘预测。这些技术依赖于在图上执行的随机游走,以捕获其结构特性。然后,这些结构属性被编码在向量表示空间中。然而,大多数当代的表示学习方法仅适用于静态图,而现实世界的图往往是动态的,并随着时间的推移而变化。静态表示学习方法不能在图形改变时更新矢量表示;因此,它们必须在图形的更新的静态快照上重新生成矢量表示,而不管图形中的改变程度如何。在这项工作中,我们提出了计算效率高的算法顶点表示学习,扩展随机游走为基础的方法,动态图。我们的算法的计算复杂度取决于变化的程度和速率(每次更新改变的边的数量)和图的密度。我们在现实世界数据集上经验性地评估了我们的算法,以用于多类和多标签顶点分类的下游机器学习任务。结果表明,我们的算法可以实现竞争力的结果,国家的最先进的方法,同时计算效率。

英文摘要:

An important part of many machine learning workflows on graphs is vertex representation learning, i.e., learning a low-dimensional vector representation for each vertex in the graph. Recently, several powerful techniques for unsupervised representation learning have been demonstrated to give the state-of-the-art performance in downstream tasks such as vertex classification and edge prediction. These techniques rely on random walks performed on the graph in order to capture its structural properties. These structural properties are then encoded in the vector representation space. However, most contemporary representation learning methods only apply to static graphs while real-world graphs are often dynamic and change over time. Static representation learning methods are not able to update the vector representations when the graph changes; therefore, they must re-generate the vector representations on an updated static snapshot of the graph regardless of the extent of the change in the graph. In this work, we propose computationally efficient algorithms for vertex representation learning that extend random walk based methods to dynamic graphs. The computation complexity of our algorithms depends upon the extent and rate of changes (the number of edges changed per update) and on the density of the graph. We empirically evaluate our algorithms on real world datasets for downstream machine learning tasks of multi-class and multi-label vertex classification. The results show that our algorithms can achieve competitive results to the state-of-the-art methods while being computationally efficient.

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。

↑