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 2105.04770cs.ITcs.LGeess.SPmath.ITmath.STstat.MLstat.TH
收藏

一般超图随机块模型的精确恢复

Exact Recovery in the General Hypergraph Stochastic Block Model

Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);National University of Singapore(新加坡国立大学)

Qiaosheng Zhang, Vincent Y. F. Tan

摘要:

本文研究了一般d-一致超图随机块模型(d-HSBM)的精确恢复的基本极限,其中n个节点被划分为k个相对大小为(p1,.,pk)。基数为d的每个节点子集都独立地生成为d阶超边,其概率取决于d个节点所属的地面实况社区。目标是根据观察到的超图准确地恢复k个隐藏社区。我们表明,存在一个尖锐的阈值,使确切的恢复是可以实现的阈值以上,不可能低于阈值(除了一个小政权的参数,将被精确指定)。这一阈值表示在一个数量,我们称之为社区之间的广义B-H分歧。我们的结果,这个一般模型恢复先前的结果为标准的SBM和d-HSBM两个对称社区作为特殊情况。在证明我们的可实现性结果的过程中,我们开发了一个满足阈值的多项式时间两阶段算法。第一阶段采用一定的超图谱聚类方法来获得社区的粗略估计,第二阶段通过局部细化步骤单独细化每个节点,以确保准确的恢复。

英文摘要:

This paper investigates fundamental limits of exact recovery in the general d-uniform hypergraph stochastic block model (d-HSBM), wherein n nodes are partitioned into k disjoint communities with relative sizes (p1,..., pk). Each subset of nodes with cardinality d is generated independently as an order-d hyperedge with a certain probability that depends on the ground-truth communities that the d nodes belong to. The goal is to exactly recover the k hidden communities based on the observed hypergraph. We show that there exists a sharp threshold such that exact recovery is achievable above the threshold and impossible below the threshold (apart from a small regime of parameters that will be specified precisely). This threshold is represented in terms of a quantity which we term as the generalized Chernoff-Hellinger divergence between communities. Our result for this general model recovers prior results for the standard SBM and d-HSBM with two symmetric communities as special cases. En route to proving our achievability results, we develop a polynomial-time two-stage algorithm that meets the threshold. The first stage adopts a certain hypergraph spectral clustering method to obtain a coarse estimate of communities, and the second stage refines each node individually via local refinement steps to ensure exact recovery.

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。

↑