Modeling Temporal Evolution and Multiscale Structure in Networks

Tue Herlau; Morten Mørup; Mikkel Nørgaard Schmidt

Modeling Temporal Evolution and Multiscale Structure in Networks

Tue Herlau, Morten Mørup, Mikkel Nørgaard Schmidt

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

189 Downloads (Pure)

Abstract

Many real-world networks exhibit both temporal evolution and multiscale structure. We propose a model for temporally correlated multifurcating hierarchies in complex networks which jointly capture both effects. We use the Gibbs fragmentation tree as prior over multifurcating trees and a change-point model to account for the temporal evolution of each vertex. We demonstrate that our model is able to infer time-varying multiscale structure in synthetic as well as three real world time-evolving complex networks. Our modeling of the temporal evolution of hierarchies brings new insights into the changing roles and position of entities and possibilities for better understanding these dynamic complex systems.

Original language	English
Title of host publication	Proceedings of the 30 th International Conference on Machine Learning
Publication date	2013
Pages	960-968
Publication status	Published - 2013
Event	30th International Conference on Machine Learning (ICML 2013) - Atlanta, Georgia, United States Duration: 16 Jun 2013 → 21 Jun 2013 http://icml.cc/2013/

Conference

Conference	30th International Conference on Machine Learning (ICML 2013)
Country/Territory	United States
City	Atlanta, Georgia
Period	16/06/2013 → 21/06/2013
Internet address	http://icml.cc/2013/

Series	JMLR: Workshop and Conference Proceedings
Number	Cycle 3
Volume	28
ISSN	1938-7228

Access to Document

Herlau13Final published version, 3.34 MB
SupplementaryFinal published version, 187 KB

http://jmlr.org/proceedings/papers/v28/

SFX availability

Full text

Cite this

@inproceedings{ee79606fd86543e7a8805423bd73d5d6,

title = "Modeling Temporal Evolution and Multiscale Structure in Networks",

abstract = "Many real-world networks exhibit both temporal evolution and multiscale structure. We propose a model for temporally correlated multifurcating hierarchies in complex networks which jointly capture both effects. We use the Gibbs fragmentation tree as prior over multifurcating trees and a change-point model to account for the temporal evolution of each vertex. We demonstrate that our model is able to infer time-varying multiscale structure in synthetic as well as three real world time-evolving complex networks. Our modeling of the temporal evolution of hierarchies brings new insights into the changing roles and position of entities and possibilities for better understanding these dynamic complex systems.",

author = "Tue Herlau and Morten M{\o}rup and Schmidt, {Mikkel N{\o}rgaard}",

year = "2013",

language = "English",

series = "JMLR: Workshop and Conference Proceedings",

number = "Cycle 3",

pages = "960--968",

booktitle = "Proceedings of the 30 th International Conference on Machine Learning",

note = "30th International Conference on Machine Learning (ICML 2013) ; Conference date: 16-06-2013 Through 21-06-2013",

url = "http://icml.cc/2013/",

}

Herlau, T , Mørup, M & Schmidt, MN 2013, Modeling Temporal Evolution and Multiscale Structure in Networks. in Proceedings of the 30 th International Conference on Machine Learning. JMLR: Workshop and Conference Proceedings, no. Cycle 3, vol. 28, pp. 960-968, 30th International Conference on Machine Learning (ICML 2013), Atlanta, Georgia, United States, 16/06/2013. <http://jmlr.org/proceedings/papers/v28/>

Modeling Temporal Evolution and Multiscale Structure in Networks. / Herlau, Tue ; Mørup, Morten ; Schmidt, Mikkel Nørgaard.

Proceedings of the 30 th International Conference on Machine Learning. 2013. p. 960-968 (JMLR: Workshop and Conference Proceedings; No. Cycle 3, Vol. 28).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Modeling Temporal Evolution and Multiscale Structure in Networks

AU - Herlau, Tue

AU - Mørup, Morten

AU - Schmidt, Mikkel Nørgaard

PY - 2013

Y1 - 2013

N2 - Many real-world networks exhibit both temporal evolution and multiscale structure. We propose a model for temporally correlated multifurcating hierarchies in complex networks which jointly capture both effects. We use the Gibbs fragmentation tree as prior over multifurcating trees and a change-point model to account for the temporal evolution of each vertex. We demonstrate that our model is able to infer time-varying multiscale structure in synthetic as well as three real world time-evolving complex networks. Our modeling of the temporal evolution of hierarchies brings new insights into the changing roles and position of entities and possibilities for better understanding these dynamic complex systems.

AB - Many real-world networks exhibit both temporal evolution and multiscale structure. We propose a model for temporally correlated multifurcating hierarchies in complex networks which jointly capture both effects. We use the Gibbs fragmentation tree as prior over multifurcating trees and a change-point model to account for the temporal evolution of each vertex. We demonstrate that our model is able to infer time-varying multiscale structure in synthetic as well as three real world time-evolving complex networks. Our modeling of the temporal evolution of hierarchies brings new insights into the changing roles and position of entities and possibilities for better understanding these dynamic complex systems.

M3 - Article in proceedings

T3 - JMLR: Workshop and Conference Proceedings

SP - 960

EP - 968

BT - Proceedings of the 30 th International Conference on Machine Learning

T2 - 30th International Conference on Machine Learning (ICML 2013)

Y2 - 16 June 2013 through 21 June 2013

ER -

Modeling Temporal Evolution and Multiscale Structure in Networks

Abstract

Conference

Access to Document

SFX availability

Fingerprint

Cite this