Clustering is an important statistical tool for the analysis of unsupervised data. Spectral clustering and stochastic block models, based on networks and graphs, are well established and widely used for community detection among many clustering algorithms. In this paper we review and discuss important statistical issues in spectral clustering and stochastic block models.

中文翻译：

---

谱聚类和随机块模型综述

聚类是用于分析非监督数据的重要统计工具。基于网络和图形的谱聚类和随机块模型已经很好地建立并广泛用于许多聚类算法中的社区检测。在本文中，我们回顾并讨论了频谱聚类和随机块模型中的重要统计问题。