arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.08572cs.SIcs.LG
收藏

网络中的邻近性和基于角色的结构嵌入:误解、技术和应用

On Proximity and Structural Role-based Embeddings in Networks: Misconceptions, Techniques, and Applications

Adobe Research(Adobe 研究院);University of Michigan(密歇根大学);Intel Labs(英特尔研究院);Worcester Polytechnic Institute(伍斯特理工学院)

Ryan A. Rossi, Di Jin, Sungchul Kim, Nesreen K. Ahmed, Danai Koutra, John Boaz Lee

摘要:

结构角色定义了一组结构相似的节点,这些节点与集合内部的节点比外部的节点更相似,而社区定义了一组节点,这些节点在集合内部的连接比外部的连接更多。基于结构相似性的角色和基于邻近性的社区是根本不同但重要的互补概念。最近,结构角色的概念变得越来越重要,并且由于从保留角色概念的图中学习表示(节点/边嵌入)的工作的激增而获得了很多关注。不幸的是,最近的工作有时混淆了结构角色和社区(基于邻近性)的概念,导致对网络嵌入方法能力的误导或不正确的说法。因此,本文试图澄清结构角色和社区之间的误解和关键区别,并正式确定一般机制(例如,随机游走、特征扩散),从而产生基于社区或角色的结构嵌入。我们从理论上证明,嵌入方法的基础上,这些机制的结果,无论是社区或基于角色的结构嵌入。这些机制通常很容易识别,可以帮助研究人员快速确定一种方法是否保留了社区或基于角色的嵌入。此外,它们还可以作为开发社区或基于角色的结构嵌入的新方法和改进方法的基础。最后,我们分析并讨论了社区或基于角色的嵌入最适合的应用程序和数据特征。

英文摘要:

Structural roles define sets of structurally similar nodes that are more similar to nodes inside the set than outside, whereas communities define sets of nodes with more connections inside the set than outside. Roles based on structural similarity and communities based on proximity are fundamentally different but important complementary notions. Recently, the notion of structural roles has become increasingly important and has gained a lot of attention due to the proliferation of work on learning representations (node/edge embeddings) from graphs that preserve the notion of roles. Unfortunately, recent work has sometimes confused the notion of structural roles and communities (based on proximity) leading to misleading or incorrect claims about the capabilities of network embedding methods. As such, this paper seeks to clarify the misconceptions and key differences between structural roles and communities, and formalize the general mechanisms (e.g., random walks, feature diffusion) that give rise to community or role-based structural embeddings. We theoretically prove that embedding methods based on these mechanisms result in either community or role-based structural embeddings. These mechanisms are typically easy to identify and can help researchers quickly determine whether a method preserves community or role-based embeddings. Furthermore, they also serve as a basis for developing new and improved methods for community or role-based structural embeddings. Finally, we analyze and discuss applications and data characteristics where community or role-based embeddings are most appropriate.

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。

↑