A Multidimensional Heuristic for Social Routing in Peer-to-Peer Networks

A fundamental problem encountered in designing decentralized social applications is the issue of efficiently locating target nodes in social peer-to-peer networks based on local information only. The unique "small-world" phenomenon of social networks shows that a typical pair of nodes is connected by very short chains of intermediate friends, and individuals are able to collectively discover such short paths. In this paper, we propose a decentralized algorithm that exploits this " small-world" phenomenon to discover efficient routes to reach target nodes in unstructured social overlays. In order to test the performance of this algorithm, we simulate it on a real-world social graph dataset crawled from a large online social networking website (LiveJournal). Compared with other related works, the simulation results show that our proposed decentralized social routing algorithm not only shortens the median length of the search path, but also increases the success rate of finding such routes between arbitrary pair of nodes in the LiveJournal social graph.