Paper Info
Title
Clustering With Multi-Layer Graphs: A Spectral Perspective
Abstract
Observational data usually comes with a multimodal nature, which means that it can be naturally represented by a multi-layer graph whose layers share the same set of vertices (objects) with different edges (pairwise relationships). In this paper, we address the problem of combining different layers of the multi-layer graph for an improved clustering of the vertices compared to using layers independently. We propose two novel methods, which are based on a joint matrix factorization and a graph regularization framework respectively, to efficiently combine the spectrum of the multiple graph layers, namely the eigenvectors of the graph Laplacian matrices. In each case, the resulting combination, which we call a “joint spectrum” of multiple layers, is used for clustering the vertices. We evaluate our approaches by experiments with several real world social network datasets. Results demonstrate the superior or competitive performance of the proposed methods compared to state-of-the-art techniques and common baseline methods, such as co-regularization and summation of information from individual graphs.
Year
DOI
Venue
2012
10.1109/TSP.2012.2212886
IEEE Transactions on Signal Processing
Keywords
DocType
Volume
spectrum of the graph,vertices clustering,spectral perspective,mobile social network,graph-based regularization,pattern clustering,joint matrix factorization,graph regularization framework,multi-layer graphs,real world social network datasets,multilayer graphs,matrix decomposition,matrix factorization,graph theory,laplace equations,multimodal nature,graph laplacian matrices,clustering,spectrum,graph laplacian,clustering algorithms,mobile communication,social network,eigenvectors,sparse matrices
Journal
60
Issue
ISSN
Citations 
11
1053-587X
39
PageRank 
References 
Authors
1.40
18
4
Name
Order
Citations
PageRank
Xiaowen Dong124922.07
Pascal Frossard23015230.41
Pierre Vandergheynst33576208.25
Nikolai Nefedov412010.62