P-Rank: A Comprehensive Structural Similarity Measure Over Information Networks

Abstract

With the ubiquity of information networks and their broad applications, the issue of similarity computation between entities of an information network arises and draws extensive research interests. However, to effectively and comprehensively measure "<i>how similar two entities are within an information network</i>" is nontrivial, and the problem becomes even more challenging when the information network to be examined is massive and diverse. In this paper, we propose a new similarity measure, <b>P-Rank</b> (<b>P</b>enetrating <b>R</b>ank), toward effectively computing the structural similarities of entities in real information networks. <b>P-Rank</b> enriches the well-known similarity measure, <b>SimRank</b>, by jointly encoding both in- and out-link relationships into structural similarity computation. <b>P-Rank</b> is proven to be a unified structural similarity framework, under which all state-of-the-art similarity measures, including <b>CoCitation</b>, <b>Coupling</b>, <b>Amsler</b> and <b>SimRank</b>, are just its special cases. Based on its recursive nature of <b>P-Rank</b>, we propose a fixed point algorithm to reinforce structural similarity of vertex pairs beyond the localized neighborhood scope toward the entire information network. Our experimental studies demonstrate the power of <b>P-Rank</b> as an effective similarity measure in different information networks. Meanwhile, under the same time/space complexity, <b>P-Rank</b> outperforms <b>SimRank</b> as a comprehensive and more meaningful structural similarity measure, especially in large real information networks.