Spectral clustering of large-scale communities via random sketching and validation

In our era of data deluge, clustering algorithms that do not scale well with the dramatically increasing number of data have to be reconsidered. Spectral clustering, while powerful, is computationally and memory demanding, even for high performance computers. Capitalizing on the relationship between spectral clustering and kernel k-means, the present paper introduces a randomized algorithm for identifying communities in large-scale graphs based on a random sketching and validation approach, that enjoys reduced complexity compared to the clairvoyant spectral clustering. Numerical tests on synthetic and real data demonstrate the potential of the proposed approach.