Discovering Latent Network Structure in Point Process Data

Scott Linderman, Ryan Adams
; Proceedings of the 31st International Conference on Machine Learning, PMLR 32(2):1413-1421, 2014.

Abstract

Networks play a central role in modern data analysis, enabling us to reason about systems by studying the relationships between their parts. Most often in network analysis, the edges are given. However, in many systems it is difficult or impossible to measure the network directly. Examples of latent networks include economic interactions linking financial instruments and patterns of reciprocity in gang violence. In these cases, we are limited to noisy observations of events associated with each node. To enable analysis of these implicit networks, we develop a probabilistic model that combines mutually-exciting point processes with random graph models. We show how the Poisson superposition principle enables an elegant auxiliary variable formulation and a fully-Bayesian, parallel inference algorithm. We evaluate this new model empirically on several datasets.

Cite this Paper


BibTeX
@InProceedings{pmlr-v32-linderman14, title = {Discovering Latent Network Structure in Point Process Data}, author = {Scott Linderman and Ryan Adams}, booktitle = {Proceedings of the 31st International Conference on Machine Learning}, pages = {1413--1421}, year = {2014}, editor = {Eric P. Xing and Tony Jebara}, volume = {32}, number = {2}, series = {Proceedings of Machine Learning Research}, address = {Bejing, China}, month = {22--24 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v32/linderman14.pdf}, url = {http://proceedings.mlr.press/v32/linderman14.html}, abstract = {Networks play a central role in modern data analysis, enabling us to reason about systems by studying the relationships between their parts. Most often in network analysis, the edges are given. However, in many systems it is difficult or impossible to measure the network directly. Examples of latent networks include economic interactions linking financial instruments and patterns of reciprocity in gang violence. In these cases, we are limited to noisy observations of events associated with each node. To enable analysis of these implicit networks, we develop a probabilistic model that combines mutually-exciting point processes with random graph models. We show how the Poisson superposition principle enables an elegant auxiliary variable formulation and a fully-Bayesian, parallel inference algorithm. We evaluate this new model empirically on several datasets.} }
Endnote
%0 Conference Paper %T Discovering Latent Network Structure in Point Process Data %A Scott Linderman %A Ryan Adams %B Proceedings of the 31st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2014 %E Eric P. Xing %E Tony Jebara %F pmlr-v32-linderman14 %I PMLR %J Proceedings of Machine Learning Research %P 1413--1421 %U http://proceedings.mlr.press %V 32 %N 2 %W PMLR %X Networks play a central role in modern data analysis, enabling us to reason about systems by studying the relationships between their parts. Most often in network analysis, the edges are given. However, in many systems it is difficult or impossible to measure the network directly. Examples of latent networks include economic interactions linking financial instruments and patterns of reciprocity in gang violence. In these cases, we are limited to noisy observations of events associated with each node. To enable analysis of these implicit networks, we develop a probabilistic model that combines mutually-exciting point processes with random graph models. We show how the Poisson superposition principle enables an elegant auxiliary variable formulation and a fully-Bayesian, parallel inference algorithm. We evaluate this new model empirically on several datasets.
RIS
TY - CPAPER TI - Discovering Latent Network Structure in Point Process Data AU - Scott Linderman AU - Ryan Adams BT - Proceedings of the 31st International Conference on Machine Learning PY - 2014/01/27 DA - 2014/01/27 ED - Eric P. Xing ED - Tony Jebara ID - pmlr-v32-linderman14 PB - PMLR SP - 1413 DP - PMLR EP - 1421 L1 - http://proceedings.mlr.press/v32/linderman14.pdf UR - http://proceedings.mlr.press/v32/linderman14.html AB - Networks play a central role in modern data analysis, enabling us to reason about systems by studying the relationships between their parts. Most often in network analysis, the edges are given. However, in many systems it is difficult or impossible to measure the network directly. Examples of latent networks include economic interactions linking financial instruments and patterns of reciprocity in gang violence. In these cases, we are limited to noisy observations of events associated with each node. To enable analysis of these implicit networks, we develop a probabilistic model that combines mutually-exciting point processes with random graph models. We show how the Poisson superposition principle enables an elegant auxiliary variable formulation and a fully-Bayesian, parallel inference algorithm. We evaluate this new model empirically on several datasets. ER -
APA
Linderman, S. & Adams, R.. (2014). Discovering Latent Network Structure in Point Process Data. Proceedings of the 31st International Conference on Machine Learning, in PMLR 32(2):1413-1421

Related Material