000166753 001__ 166753
000166753 005__ 20190821050242.0
000166753 022__ $$a1053-587X
000166753 0247_ $$2doi$$a10.1109/Tsp.2012.2212886
000166753 02470 $$2ISI$$a000310139900017
000166753 02470 $$2arXiv$$a1106.2233
000166753 037__ $$aARTICLE
000166753 245__ $$aClustering with Multi-Layer Graphs: A Spectral Perspective
000166753 269__ $$a2012
000166753 260__ $$bInstitute of Electrical and Electronics Engineers$$c2012$$aPiscataway
000166753 300__ $$a12
000166753 336__ $$aJournal Articles
000166753 520__ $$aObservational 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 (users) with different edges (pairwise relationships). In this paper, we address the problem of combining different layers of the multi-layer graph for improved clustering of the vertices compared to using layers independently. We propose two novel methods, which are based on joint matrix factorization and 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 graphs, is used for clustering the vertices. We evaluate our approaches by simulations with several real world social network datasets. Results demonstrate the superior or competitive performance of the proposed methods over state-of-the-art technique and common baseline methods, such as co-regularization and summation of information from individual graphs.
000166753 6531_ $$aMulti-layer graph
000166753 6531_ $$aspectrum of the graph
000166753 6531_ $$amatrix factorization
000166753 6531_ $$agraph-based regularization
000166753 6531_ $$aclustering
000166753 6531_ $$aLTS4
000166753 6531_ $$aLTS2
000166753 700__ $$0242933$$g193962$$aDong, Xiaowen
000166753 700__ $$0241061$$g101475$$aFrossard, Pascal
000166753 700__ $$0240428$$g120906$$aVandergheynst, Pierre
000166753 700__ $$aNefedov, Nikolai
000166753 773__ $$j60$$tIEEE Transactions on Signal Processing$$k11$$q5820-5831
000166753 909C0 $$xU10851$$0252393$$pLTS4
000166753 909C0 $$xU10380$$0252392$$pLTS2
000166753 909CO $$qGLOBAL_SET$$pSTI$$particle$$ooai:infoscience.tind.io:166753
000166753 917Z8 $$x193962
000166753 917Z8 $$x193962
000166753 917Z8 $$x193962
000166753 917Z8 $$x193962
000166753 917Z8 $$x193962
000166753 917Z8 $$x101475
000166753 917Z8 $$x101475
000166753 917Z8 $$x193962
000166753 937__ $$aEPFL-ARTICLE-166753
000166753 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000166753 980__ $$aARTICLE