度相关随机块模型的密度演化
Density Evolution in the Degree-correlated Stochastic Block Model
摘要:
最近,在随机块模型下确定簇恢复的急剧恢复阈值的兴趣激增。在本文中,我们解决了更精细的问题,平均有多少顶点会被错误分类。我们考虑二进制形式的随机块模型,其中$n$顶点被划分为两个集群与边缘概率$a/n$内的第一个集群,$c/n$内的第二个集群,和$b/n$跨集群。设为$n \to \infty$,$a= b+ μ\sqrt{ b} $,$c=b+ ν\sqrt{ b} $为两个固定常数$μ, ν$,而$b \to \infty$为$b=n^{o(1)}$ .当簇的大小是平衡的和$μ\neq ν$,我们表明,平均错误分类的顶点的最小分数是由$Q(\sqrt{v^*})$,其中$Q(x)$是标准正常的Q-函数,$v^*$是唯一的不动点的$v= \frac{(μ-ν)^2}{16} + \frac{ (μ+ν)^2 }{16} \mathbb{E}[ \tanh(v+ \sqrt{v} Z)],$和$Z$是标准正常的。此外,最小的误分类分数平均获得的局部算法,即信念传播,在时间上的线性的边缘的数量。我们的证明技术的基础上连接的集群恢复问题的树重建问题,并分析密度的高斯近似树上的信念传播的演变。
英文摘要:
There is a recent surge of interest in identifying the sharp recovery thresholds for cluster recovery under the stochastic block model. In this paper, we address the more refined question of how many vertices that will be misclassified on average. We consider the binary form of the stochastic block model, where $n$ vertices are partitioned into two clusters with edge probability $a/n$ within the first cluster, $c/n$ within the second cluster, and $b/n$ across clusters. Suppose that as $n \to \infty$, $a= b+ μ\sqrt{ b} $, $c=b+ ν\sqrt{ b} $ for two fixed constants $μ, ν$, and $b \to \infty$ with $b=n^{o(1)}$. When the cluster sizes are balanced and $μ\neq ν$, we show that the minimum fraction of misclassified vertices on average is given by $Q(\sqrt{v^*})$, where $Q(x)$ is the Q-function for standard normal, $v^*$ is the unique fixed point of $v= \frac{(μ-ν)^2}{16} + \frac{ (μ+ν)^2 }{16} \mathbb{E}[ \tanh(v+ \sqrt{v} Z)],$ and $Z$ is standard normal. Moreover, the minimum misclassified fraction on average is attained by a local algorithm, namely belief propagation, in time linear in the number of edges. Our proof techniques are based on connecting the cluster recovery problem to tree reconstruction problems, and analyzing the density evolution of belief propagation on trees with Gaussian approximations.
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。