Change-Point Detection in Dynamic Networks with Missing Links

• 成果类型: Article
• 署名作者: Enikeeva, Farida; Klopp, Olga
• 署名单位: Universite de Poitiers
• 刊物名称: OPERATIONS RESEARCH
• ISSN/ISSBN: 0030-364X
• DOI: 10.1287/opre.2021.0413
• 发表日期: 2025
• 关键词: time-series; SPARSE

摘要

Structural changes occur in dynamic networks quite frequently and their detection is an important question in many situations, such as fraud detection or cybersecurity. Real-life networks are often incompletely observed because of individual nonresponse or network size. In the present paper, we consider the problem of change-point detection at a temporal sequence of partially observed networks. The goal is to test whether there is a change in the network parameters. Our approach is based on the matrix cumulative sum test statistic and allows growing the size of networks. We show that the proposed test is minimax optimal and robust to missing links. We also demonstrate the good behavior of our approach in practice through simulation study and a real-data application.