arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.10255cs.LG
收藏

具有持久同源性的链接预测:交互式视图

Link Prediction with Persistent Homology: An Interactive View

Peking University(北京大学);IBM(国际商业机器公司);Stony Brook University(石溪大学)

Zuoyu Yan, Tengfei Ma, Liangcai Gao, Zhi Tang, Chao Chen

摘要:

链接预测是图结构数据的一项重要学习任务。在本文中,我们提出了一种新的拓扑方法来描述两个节点之间的相互作用。我们的拓扑特征,基于扩展的持久同源性,编码丰富的结构信息的多跳路径连接节点。基于这一特点,我们提出了一个图神经网络的方法,优于国家的最先进的在不同的基准。作为另一个贡献,我们提出了一种新的算法,更有效地计算扩展持久图的图。该算法可以普遍应用于加速许多其他拓扑方法的图学习任务。

英文摘要:

Link prediction is an important learning task for graph-structured data. In this paper, we propose a novel topological approach to characterize interactions between two nodes. Our topological feature, based on the extended persistent homology, encodes rich structural information regarding the multi-hop paths connecting nodes. Based on this feature, we propose a graph neural network method that outperforms state-of-the-arts on different benchmarks. As another contribution, we propose a novel algorithm to more efficiently compute the extended persistence diagrams for graphs. This algorithm can be generally applied to accelerate many other topological methods for graph learning tasks.

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。

↑