Current flow betweeness centrality with Apache Spark

The identication of the most central nodes of a graph is a fundamental task of data analysis. The current ow betweenness is a centrality index which considers how the information ows along all the paths of a graph, not only on the shortest ones. Finding the exact value of the current ow betweenness is computationally expensive for large graphs, so the denition of algorithms returning an approximation of this measure is mandatory. In this paper we propose a solution that estimates the current ow betweenness in a distributed setting using the Apache Spark framework. The computation is dened and organized for the dis- tributed environment in order to provide an approximate solution within an acceptable computational time. Our experimental evaluation shows that the algorithm achieves high correlation with the exact value of the current ow betweenness, is scalable and outperforms other algorithms.