arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.02896stat.MLcs.AIcs.SIstat.AP
收藏

学习基于角色的图嵌入

Learning Role-based Graph Embeddings

Intel Labs(英特尔研究院);Adobe Research(奥多比研究院);WPI(伍斯特理工学院);Google(谷歌);Xerox PARC(施乐帕洛阿尔托研究中心)

Nesreen K. Ahmed, Ryan Rossi, John Boaz Lee, Theodore L. Willke, Rong Zhou, Xiangnan Kong, Hoda Eldardiry

摘要:

随机游动是许多现有网络嵌入方法的核心。然而,这样的算法具有由于使用随机游动而产生的许多限制,例如,由这些方法产生的特征不能转移到新的节点和图,因为它们与顶点身份有关。在这项工作中,我们引入了Role2Vec框架,它使用了灵活的属性随机游动概念,并作为推广现有方法的基础,如DeepWalk,node2vec,以及许多其他利用随机游动的方法。我们提出的框架使这些方法能够更广泛地适用于转导和归纳学习,以及用于具有属性的图(如果可用)。这是通过学习推广到新节点和图的函数来实现的。我们表明,我们提出的框架是有效的,平均AUC提高了16.55%,同时在各种图上平均需要比现有方法少853倍的空间。

英文摘要:

Random walks are at the heart of many existing network embedding methods. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to vertex identity. In this work, we introduce the Role2Vec framework which uses the flexible notion of attributed random walks, and serves as a basis for generalizing existing methods such as DeepWalk, node2vec, and many others that leverage random walks. Our proposed framework enables these methods to be more widely applicable for both transductive and inductive learning as well as for use on graphs with attributes (if available). This is achieved by learning functions that generalize to new nodes and graphs. We show that our proposed framework is effective with an average AUC improvement of 16.55% while requiring on average 853x less space than existing methods on a variety of graphs.

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。

↑