|
Activity Number:
|
307
- Novel Approaches for Analyzing Dynamic Networks
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 30, 2019 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistical Learning and Data Science
|
|
Abstract #304727
|
Presentation
|
|
Title:
|
Anomaly Detection in Time-Varying Networks
|
|
Author(s):
|
Lata Kodali* and Leanna House and Srijan Sengupta and William H. Woodall
|
|
Companies:
|
Virginia Tech and Virginia Tech and VIrginia Tech and Virginia Tech
|
|
Keywords:
|
Networks;
Temporal;
Anomaly Detection
|
|
Abstract:
|
Network data has emerged as an active research area in statistics. However, much of the focus of ongoing research has been on static networks which are invariant over time. Monitoring time-varying networks to detect anomalous changes has applications in both social and physical sciences. In this work, we propose a general framework for anomaly detection in time-varying networks by incorporating principles from statistical process monitoring. We show that our method works in a variety of well-studied networks models (e.g., a dynamic latent space model and a dynamic degree-corrected stochastic blockmodel) in the context of a simulation study as well as in applications involving well-known network datasets.
|
Authors who are presenting talks have a * after their name.
