Options
Joint Modelling of Multiple Network Views
Author(s)
Date Issued
2014-11-17
Date Available
2016-05-17T01:00:17Z
Abstract
Latent space models (LSM) for network data were introduced by Holf et al. (2002) under the basic assumption that each node of the network has an unknown position in a D-dimensional Euclidean latent space: generally the smaller the distance between two nodes in the latent space, the greater their probability of being connected. In this paper we propose a variational inference approach to estimate the intractable posterior of the LSM. In many cases, different network views on the same set of nodes are available. It can therefore be useful to build a model able to jointly summarise the information given by all the network views. For this purpose, we introduce the latent space joint model (LSJM) that merges the information given by multiple network views assuming that the probability of a node being connected with other nodes in each network view is explained by a unique latent variable. This model is demonstrated on the analysis of two datasets: an excerpt of 50 girls from 'Teenage Friends and Lifestyle Study' data at three time points and the Saccharomyces cerevisiae genetic and physical protein-protein interactions.
Other Sponsorship
Science Foundation Ireland
Type of Material
Journal Article
Publisher
Taylor and Francis
Journal
Journal of Computational and Graphical Statistics
Copyright (Published Version)
2014 Taylor and Francis
Web versions
Language
English
Status of Item
Peer reviewed
This item is made available under a Creative Commons License
File(s)
Owning collection
Views
1887
Last Week
1
1
Last Month
5
5
Acquisition Date
Mar 19, 2024
Mar 19, 2024
Downloads
409
Last Week
2
2
Last Month
7
7
Acquisition Date
Mar 19, 2024
Mar 19, 2024