arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1405.3267cs.SImath.PRphysics.soc-ph
收藏

随机块模型的精确恢复

Exact Recovery in the Stochastic Block Model

Emmanuel Abbe, Afonso S. Bandeira, Georgina Hall

摘要:

具有两个社区的随机块模型(SBM),或者等价于种植二分模型,是一种流行的具有聚类行为的随机图模型。在对称的情况下,图有两个大小相等的簇,并且顶点以簇内概率$p$和簇间概率$q$连接。在过去的二十年里,大量的统计学和计算机科学文献都集中在提供$|p-q|$的缩放下限,以确保准确的恢复。在本文中,我们确定了一个尖锐的阈值现象,准确的恢复:如果$α=pn/\log(n)$和$β=qn/\log(n)$是恒定的(与$α>β$),恢复社区与高概率是可能的,如果$\frac{α+β}{2} - \sqrt{αβ}>1$和不可能的,如果$\frac{α+β}{2} - \sqrt{αβ}<1$。特别是,这改善了现有的边界。这也为高效的聚类算法提供了新的思路。虽然最大似然(ML)达到了最佳阈值(根据定义),但它在最坏情况下是NP困难的。本文提出了一种基于ML的半定规划松弛的有效算法,该算法被证明能够成功地恢复出接近阈值的社区,数值实验表明该算法可以达到阈值。一个有效的算法,成功所有的方式下降到阈值也得到了使用局部改进过程相结合的部分恢复算法。

英文摘要:

The stochastic block model (SBM) with two communities, or equivalently the planted bisection model, is a popular model of random graph exhibiting a cluster behaviour. In the symmetric case, the graph has two equally sized clusters and vertices connect with probability $p$ within clusters and $q$ across clusters. In the past two decades, a large body of literature in statistics and computer science has focused on providing lower-bounds on the scaling of $|p-q|$ to ensure exact recovery. In this paper, we identify a sharp threshold phenomenon for exact recovery: if $α=pn/\log(n)$ and $β=qn/\log(n)$ are constant (with $α>β$), recovering the communities with high probability is possible if $\frac{α+β}{2} - \sqrt{αβ}>1$ and impossible if $\frac{α+β}{2} - \sqrt{αβ}<1$. In particular, this improves the existing bounds. This also sets a new line of sight for efficient clustering algorithms. While maximum likelihood (ML) achieves the optimal threshold (by definition), it is in the worst-case NP-hard. This paper proposes an efficient algorithm based on a semidefinite programming relaxation of ML, which is proved to succeed in recovering the communities close to the threshold, while numerical experiments suggest it may achieve the threshold. An efficient algorithm which succeeds all the way down to the threshold is also obtained using a partial recovery algorithm combined with a local improvement procedure.

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。

↑