arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.02802math.PR
收藏

在具有几何核的块模型中进行社区检测

Community Detection on Block Models with Geometric Kernels

INRIA(法国国家信息与自动化研究所);Eindhoven University of Technology(埃因霍温理工大学);Aalto University(阿尔托大学)

Konstantin Avrachenkov, B. R. Vinay Kumar, Lasse Leskelä

AI总结:

研究在随机几何图中通过几何核恢复社区标签的统计极限,并提出线性时间算法实现信息理论阈值内的精确恢复。

摘要:

我们考虑在一组维随机几何图中进行社区恢复问题,其中每个节点有两个独立标签:一个观测位置标签和一个隐藏社区标签。几何核将节点对的位置映射到概率。根据社区和核值,节点对之间绘制边。给定生成的图及位置标签,需推断节点的潜在社区。本文将探讨此类模型中恢复社区的基本统计极限,并提出一个线性时间算法(在边数上),证明该算法在信息理论阈值内可精确恢复节点社区。

英文摘要:

We consider the community recovery problem on a one-dimensional random geometric graph where every node has two independent labels: an observed location label and a hidden community label. A geometric kernel maps the locations of pairs of nodes to probabilities. Edges are drawn between pairs of nodes based on their communities and the value of the kernel corresponding to the respective node locations. Given the graph so generated along with the location labels, the latent communities of the nodes are to be inferred. In this work, we will look into the fundamental statistical limits for recovering the communities in such models. Additionally, we propose a linear-time algorithm (in the number of edges) and show that it recovers the communities of nodes exactly up to the information theoretic threshold.

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。

↑