Imperial College London
Portrait Picture

Professor Nick Heard

Faculty of Natural Sciences, Department of Mathematics

Chair in Statistics
 
 
 
//

Contact

 

+44 (0)20 7594 1490n.heard Website

 
 
//

Location

 

543Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Sanna:2023:10.1080/10618600.2022.2096048,
author = {Sanna, Passino F and Heard, NA},
doi = {10.1080/10618600.2022.2096048},
journal = {Journal of Computational and Graphical Statistics},
pages = {116--130},
title = {Mutually exciting point process graphs for modelling dynamic networks},
url = {http://dx.doi.org/10.1080/10618600.2022.2096048},
volume = {32},
year = {2023}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - A new class of models for dynamic networks is proposed, called mutually exciting point process graphs (MEG). MEG is a scalable network-wide statistical model for point processes with dyadic marks, which can be used for anomaly detection when assessing the significance of future events, including previously unobserved connections between nodes. The model combines mutually exciting point processes to estimate dependencies between events and latent space models to infer relationships between the nodes. The intensity functions for each network edge are characterized exclusively by node-specific parameters, which allows information to be shared across the network. This construction enables estimation of intensities even for unobserved edges, which is particularly important in real world applications, such as computer networks arising in cyber-security. A recursive form of the log-likelihood function for MEG is obtained, which is used to derive fast inferential procedures via modern gradient ascent algorithms. An alternative EM algorithm is also derived. The model and algorithms are tested on simulated graphs and real world datasets, demonstrating excellent performance. Supplementary materials for this article are available online.
AU  - Sanna,Passino F
AU  - Heard,NA
DO  - 10.1080/10618600.2022.2096048
EP  - 130
PY  - 2023///
SN  - 1061-8600
SP  - 116
TI  - Mutually exciting point process graphs for modelling dynamic networks
T2  - Journal of Computational and Graphical Statistics
UR  - http://dx.doi.org/10.1080/10618600.2022.2096048
UR  - http://hdl.handle.net/10044/1/99832
VL  - 32
ER  -
Download