Provided by: University of Florence
Topic: Big Data
In this paper, the authors consider the problem of clustering, given the similarity matrix of a set of data points or nodes; this problem is a.k.a. graph clustering. Spectral clustering techniques are typically used to solve this problem. The performance of the existing spectral clustering techniques is not satisfactory for many applications. To improve the performance, they take a bio-inspired approach to the graph clustering problem and enable fictitious queues with self-organizing capability to group similar nodes into the same cluster; they call the resulting scheme, Self-Organizing-Queue (SOQ) clustering scheme. Experimental results have demonstrated the superiority of their SOQ scheme over the existing spectral clustering techniques and K-means algorithm.