Paper Info
Title
Modelling dense relational data
Abstract
Relational modelling classically consider sparse and discrete data. Measures of influence computed pairwise between temporal sources naturally give rise to dense continuous-valued matrices, for instance p-values from Granger causality. Due to asymmetry or lack of positive definiteness they are not naturally suited for kernel K-means. We propose a generative Bayesian model for dense matrices which generalize kernel K-means to consider off-diagonal interactions in matrices of interactions, and demonstrate its ability to detect structure on both artificial data and two real data sets.
Year
DOI
Venue
2012
10.1109/MLSP.2012.6349747
Machine Learning for Signal Processing
Keywords
Field
DocType
belief networks,biomedical MRI,matrix algebra,pattern clustering,Bayesian model,Granger causality,artificial data,dense continuous-valued matrices,dense matrices,dense relational data,fMRI,instance p-values,kernel K-means,positive definiteness,real data sets,relational modelling,Granger Causality,Infinite Relational Model,Non-parametrics,Relational Modelling
Kernel (linear algebra),Pairwise comparison,Data set,Bayesian inference,Pattern recognition,Relational database,Computer science,Matrix (mathematics),Artificial intelligence,Positive definiteness,Asymmetry,Machine learning
Conference
ISSN
ISBN
Citations 
1551-2541 E-ISBN : 978-1-4673-1025-3
978-1-4673-1025-3
5
PageRank 
References 
Authors
0.55
4
4
Name
Order
Citations
PageRank
Herlau, T.150.55
Morten Mørup270451.29
Mikkel N. Schmidt327726.13
Lars Kai Hansen42776341.03