Efficient Core Decomposition Over Large Heterogeneous Information Networks

Core decomposition is a critical metric for evaluating the vertex importance and analyzing graph structure. Given a graph$G$, a k-core is the largest subgraph of$G$where each vertex has at least$k$neighbors. Most existing works mainly focus on homogeneous graphs in which edges are of the same type and cannot be applied to heterogeneous information networks (HINs) directly. However, most real-world networks are HINs which consist of different vertex types and edge types. To reveal the cohesive subgraphs with hierarchical relations on HINs, we adopt the well-known$(k,\mathcal{P})$-core model to compute coreness over HINs, where$\mathcal{P}$is a meta-path, i.e., a sequence of relations defined between different types of vertices. Hence, the$(k,\mathcal{P})$-core is a subgraph where each vertex is connected to at least$k$other vertices via instances of$\mathcal{P}$. Based on two kinds of sparse matrix products, we propose two kinds of algebraic core decomposition algorithms, which are suitable for general HINs and locally dense HINs, respectively. We have performed extensive empirical evaluations of our algorithms on six large real-world HINs. The results show that the proposed solutions are highly efficient for core decomposition and achieve up to$258.84\times$speedup than the state-of-the-art parallel algorithm on 20 cores. Moreover, other HIN tasks that involve homogeneous graph construction can also benefit from our algorithms.