Abstract
Shortest path distance query is one of the most fundamental problems in graph theory and applications. Nowadays, the scale of graphs becomes so large that traditional algorithms for shortest path are not available to answer the exact distance query quickly. Many methods based on two-hop labeling have been proposed to solve this problem. However, they cost too much either in preprocessing or query phase to handle large networks containing as many as tens of millions of vertices. In this paper, we propose a novel $k$-hub labeling method to address this problem in large networks with less preprocessing cost while keeping the query time in the microsecond level on average. Technically, two types of labels are presented in our construction, one for distance queries when the actual distance is at most $k-2$, which we call local label, and the other for further distance queries, which we call hub label. Our approach of $k$-hub labeling is essentially different from previous widely used two-hop labeling framework since we construct labels by using hub network structure. We conduct extensive experiments on large real-world networks and the results demonstrate the higher efficiency of our method in preprocessing phase and the much smaller space size of constructed index compared to previous efficient two-hop labeling method, with a comparatively fast query speed.
RDBMS Based Efficient Method for Shortest Path Searching Over Large Graphs Using K-degree Index Table
