Paper Info
Title
A Mean-Field Variational Bayesian Approach to Detecting Overlapping Communities with Inner Roles Using Poisson Link Generation.
Abstract
A novel model-based machine-learning approach is presented for the unsupervised and exploratory analysis of node affiliations to overlapping communities with roles in networks. At the heart of our approach is a new Bayesian probabilistic generative model of directed networks, that treats roles as abstract behavioral classes explaining node linking behavior. A generalized weighted instance of directed affiliation modeling rules the strength of node participation in communities with whichever role through Gamma priors. Moreover, link establishment between nodes is governed by a Poisson distribution. The latter is parameterized so that, the stronger the affiliations of two nodes to common communities with respective roles, the more likely it is the formation of a connection. A coordinate-ascent algorithm is designed to implement mean-field variational inference for affiliation analysis and link prediction. A comparative experimentation on real-world networks demonstrates the superiority of our approach in community compactness, link prediction and scalability.
Year
DOI
Venue
2016
10.1007/978-3-319-46349-0_10
ADVANCES IN INTELLIGENT DATA ANALYSIS XV
Field
DocType
Volume
Computer science,Theoretical computer science,Artificial intelligence,Poisson distribution,Parameterized complexity,Mathematical optimization,Inference,Compact space,Mean field theory,Prior probability,Machine learning,Scalability,Bayesian probability
Conference
9897
ISSN
Citations 
PageRank 
0302-9743
2
0.36
References 
Authors
12
2
Name
Order
Citations
PageRank
Gianni Costa123524.04
Riccardo Ortale228227.46