A new approach for aggregated PageRank computation via distributed randomized algorithms

At Google, the PageRank algorithm helps rankings in search results by providing measures of web page importance. This paper builds upon the distributed randomized approach for this algorithm proposed in our recent works. To reduce computation and communication, we develop a method to systematically aggregate web pages into groups by exploiting the sparsity inherent in the web. Each group computes an aggregated PageRank, which can be distributed among group members. We provide a decentralized scheme for its computation and analyze convergence properties.