|
Activity Number:
|
91
- Statistical Methods for Analysis of Time-Varying Network Data
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, July 31, 2017 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
|
Abstract #322188
|
View Presentation
|
|
Title:
|
The Block Point Process Model for Continuous-Time Event-Based Dynamic Networks
|
|
Author(s):
|
Kevin Shuai Xu* and Ruthwik Junuthula and Haghdan Maysam and Devabhaktuni Vijay
|
|
Companies:
|
University of Toledo and University of Toledo and University of Toledo and University of Toledo
|
|
Keywords:
|
dynamic network ;
point process ;
timestamped network ;
block model ;
event-based network ;
hawkes process
|
|
Abstract:
|
Many application settings involve the analysis of timestamped relations or events between a set of entities, e.g. messages between users of an on-line social network. Static and discrete-time network models are typically used as analysis tools in these settings; however, they discard a significant amount of information by aggregating events over time to form network snapshots. In this paper, we propose the block point process model (BPPM) for dynamic networks evolving in continuous time in the form of events at irregular time intervals. The BPPM is inspired by the well-known stochastic block model (SBM) for static networks. We illustrate connections between the BPPM and SBM and propose an efficient algorithm for maximum-likelihood estimation of the BPPM that scales to thousands of nodes. Finally we demonstrate that the continuous-time BPPM is superior to discrete-time network models in several prediction tasks.
|
Authors who are presenting talks have a * after their name.
