Special invited paper: The SCORE normalization, especially for heterogeneous network and text data

ZT Ke, J Jin - Stat, 2023 - Wiley Online Library
SCORE was introduced as a spectral approach to network community detection. Since many
networks have severe degree heterogeneity, the ordinary spectral clustering (OSC) …

Optimal estimation of the number of network communities

J Jin, ZT Ke, S Luo, M Wang - Journal of the American Statistical …, 2023 - Taylor & Francis
In network analysis, how to estimate the number of communities K is a fundamental problem.
We consider a broad setting where we allow severe degree heterogeneity and a wide range …

Fast network community detection with profile-pseudo likelihood methods

J Wang, J Zhang, B Liu, J Zhu, J Guo - Journal of the American …, 2023 - Taylor & Francis
The stochastic block model is one of the most studied network models for community
detection, and fitting its likelihood function on large-scale networks is known to be …

On hyperparameter tuning in general clustering problemsm

X Fan, Y Yue, P Sarkar… - … conference on machine …, 2020 - proceedings.mlr.press
Tuning hyperparameters for unsupervised learning problems is difficult in general due to the
lack of ground truth for validation. However, the success of most clustering methods …

Optimal adaptivity of signed-polygon statistics for network testing

J Jin, ZT Ke, S Luo - The Annals of Statistics, 2021 - projecteuclid.org
Optimal adaptivity of signed-polygon statistics for network testing Page 1 The Annals of
Statistics 2021, Vol. 49, No. 6, 3408–3433 https://doi.org/10.1214/21-AOS2089 © Institute of …

Two-sample test of stochastic block models

Q Wu, J Hu - Computational Statistics & Data Analysis, 2024 - Elsevier
In this paper, we consider the problem of two-sample test of large networks with community
structures. A test statistic is proposed based on the maximum entry of the difference between …

GBTM: Community detection and network reconstruction for noisy and time-evolving data

X Chen, J Hu, Y Chen - Information Sciences, 2024 - Elsevier
Community detection and network reconstruction are two major concerns in network
analysis. However, these two tasks are extremely challenging since most of the existing …

Wilks' theorems in the -model

T Yan, Y Li, J Xu, Y Yang, J Zhu - arXiv preprint arXiv:2211.10055, 2022 - arxiv.org
Likelihood ratio tests and the Wilks theorems have been pivotal in statistics but have rarely
been explored in network models with an increasing dimension. We are concerned here …

Two-sample test for stochastic block models via maximum entry-wise deviation

K Fu, J Hu, S Keita, H Liu - arXiv preprint arXiv:2211.08668, 2022 - arxiv.org
The stochastic block model is a popular tool for detecting community structures in network
data. Detecting the difference between two community structures is an important issue for …

Profile‐pseudo likelihood methods for community detection of multilayer stochastic block models

K Fu, J Hu - Stat, 2023 - Wiley Online Library
The multilayer stochastic block model is one of the fundamental models in multilayer
networks and is often used to represent multiple types of relations between different …