000212742 001__ 212742
000212742 005__ 20190317000308.0
000212742 020__ $$a978-1-4799-9988-0
000212742 022__ $$a1520-6149
000212742 02470 $$2ISI$$a000388373404048
000212742 037__ $$aCONF
000212742 245__ $$aAccelerated Spectral Clustering Using Graph Filtering of Random Signals
000212742 260__ $$bIeee$$c2016$$aNew York
000212742 269__ $$a2016
000212742 300__ $$a5
000212742 336__ $$aConference Papers
000212742 490__ $$aInternational Conference on Acoustics Speech and Signal Processing ICASSP
000212742 520__ $$aWe build upon recent advances in graph signal processing to propose a faster spectral clustering algorithm. Indeed, classical spectral clustering is based on the computation of the first $k$ eigenvectors of the similarity matrix' Laplacian, whose computation cost, even for sparse matrices, becomes prohibitive for large datasets. We show that we can estimate the spectral clustering distance matrix without computing these eigenvectors: by graph filtering random signals. Also, we take advantage of the stochasticity of these random vectors to estimate the number of clusters $k$. We compare our method to classical spectral clustering on synthetic data, and show that it reaches equal performance while being faster by a factor at least two for large datasets.
000212742 6531_ $$agraph signal processing
000212742 6531_ $$aspectral clustering
000212742 700__ $$aTremblay, Nicolas
000212742 700__ $$0242927$$g179918$$aPuy, Gilles
000212742 700__ $$aBorgnat, Pierre
000212742 700__ $$aGribonval, Rémi
000212742 700__ $$0240428$$g120906$$aVandergheynst, Pierre
000212742 7112_ $$cShanghai, China$$a41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016)
000212742 773__ $$t2016 Ieee International Conference On Acoustics, Speech And Signal Processing Proceedings$$q4094-4098
000212742 8564_ $$uhttps://infoscience.epfl.ch/record/212742/files/ICASSP_2016_lap.pdf$$zPreprint$$s670957$$yPreprint
000212742 909C0 $$xU10380$$0252392$$pLTS2
000212742 909CO $$ooai:infoscience.tind.io:212742$$qGLOBAL_SET$$pconf$$pSTI
000212742 917Z8 $$x120906
000212742 917Z8 $$x120906
000212742 917Z8 $$x120906
000212742 917Z8 $$x120906
000212742 937__ $$aEPFL-CONF-212742
000212742 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000212742 980__ $$aCONF