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 2109.01494cs.LGcs.AIcs.DS
收藏

在边流上计算图描述子

Computing Graph Descriptors on Edge Streams

Rochester Institute of Technology(罗切斯特理工学院);Georgia State University(佐治亚州立大学);Lahore University of Management Sciences(拉合尔管理科学大学);Information Technology University(信息技术大学);University of Texas at Dallas(德克萨斯大学达拉斯分校)

Zohair Raza Hassan, Sarwan Ali, Imdadullah Khan, Mudassir Shabbir, Waseem Abbas

AI总结:

本文提出在边流上近似计算三种图描述子的流式算法,通过控制样本量避免全图内存存储并约束运行时间,在数百万边图上实现高效计算,且以仅25%内存达到与最先进方法相当的预测精度。

摘要:

特征提取是图分析中的一项基本任务。这些特征向量被称为图描述子,用于下游基于向量空间的图分析模型。这一思想在过去已被证明卓有成效,其中基于谱的图描述子提供了最先进的分类精度。然而,已知用于计算有意义描述子的算法无法扩展到大型图,原因在于:(1) 它们需要将整个图存储在内存中,以及 (2) 终端用户无法控制算法的运行时间。在本文中,我们提出了流式算法来近似计算三种不同的图描述子,以捕捉图的基本结构。在边流上操作使我们能够避免将整个图存储在内存中,而控制样本量使我们能够将算法的运行时间保持在期望的范围内。我们通过分析近似误差和分类精度来证明所提出描述子的有效性。我们的可扩展算法能在几分钟内计算出具有数百万条边的图的描述子。此外,这些描述子产生了与最先进方法相当的预测精度,但仅需使用 25% 的内存。

英文摘要:

Feature extraction is an essential task in graph analytics. These feature vectors, called graph descriptors, are used in downstream vector-space-based graph analysis models. This idea has proved fruitful in the past, with spectral-based graph descriptors providing state-of-the-art classification accuracy. However, known algorithms to compute meaningful descriptors do not scale to large graphs since: (1) they require storing the entire graph in memory, and (2) the end-user has no control over the algorithm's runtime. In this paper, we present streaming algorithms to approximately compute three different graph descriptors capturing the essential structure of graphs. Operating on edge streams allows us to avoid storing the entire graph in memory, and controlling the sample size enables us to keep the runtime of our algorithms within desired bounds. We demonstrate the efficacy of the proposed descriptors by analyzing the approximation error and classification accuracy. Our scalable algorithms compute descriptors of graphs with millions of edges within minutes. Moreover, these descriptors yield predictive accuracy comparable to the state-of-the-art methods but can be computed using only 25% as much memory.

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。

↑