Recently, there is a surge of interests on heterogeneous information network analysis, where the network includes different types of objects or links. As a newly emerging network model, heterogeneous information networks have many unique features, e.g., complex structure and rich semantics. Moreover, meta path, the sequence of relations connecting two object types, is widely used to integrate different types of objects and mine the semantics information in this kind of networks. The object ranking is an important and basic function in network analysis, which has been extensively studied in homogeneous networks including the same type of objects and links. However, it is not well exploited in heterogeneous networks until now, since the characteristics of heterogeneous networks introduce new challenges for object ranking. In this paper, we study the ranking problem in heterogeneous networks and propose the HRank method to evaluate the importance of multiple types of objects and meta paths. Since the traditional meta path coarsely embodies path semantics, we propose a constrained meta path to subtly capture the refined semantics through confining constraints on objects. Based on a path-constrained random walk process, HRank can simultaneously determine the importance of objects and constrained meta paths through applying the tensor analysis. Extensive experiments on three real datasets show that HRank can effectively evaluate the importance of objects and paths together. Moreover, the constrained meta path shows its potential on mining subtle semantics by obtaining more accurate ranking results.
