Identifiability and estimation of mixed membership stochastic blockmodels

He, Shishuang

Permalink

https://hdl.handle.net/2142/122228 Copy

Description

Title

Identifiability and estimation of mixed membership stochastic blockmodels

Author(s)

He, Shishuang

Issue Date

2023-11-30

Director of Research (if dissertation) or Advisor (if thesis)

• Liang, Feng
• Yang, Yun

Doctoral Committee Chair(s)

• Liang, Feng
• Yang, Yun

Committee Member(s)

• Chen, Yuguo
• Liu, Jingbo

Department of Study

Statistics

Discipline

Statistics

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Keyword(s)

• Mixed membership stochastic blockmodels
• Identifiability
• Volume minimization
• Sufficiently scattered
• Volume-penalized integrated likelihood

Abstract

The Mixed Membership Stochastic Blockmodel (MMSB) is a widely used method for detecting overlapping communities in large network data. However, MMSB is known to be unidentifiable, which presents a challenge for practical use. Previous approaches to MMSB identifiability rely on pure nodes, or nodes belonging to only one community, which is often too restrictive for real-world applications. In this paper, we propose a new, less restrictive set of identifiability conditions for MMSB and introduce an estimator based on a specific integrated likelihood with a penalty for volume. Our proposed estimator is demonstrated to have desirable asymptotic properties and can be efficiently computed using an MCMC-EM algorithm. We illustrate the benefits of our method through simulation studies and real data applications.

Graduation Semester

2023-12

Type of Resource

Thesis

Handle URL

https://hdl.handle.net/2142/122228

Copyright and License Information

Copyright 2023 Shishuang He

Owning Collections