PROJECT TITLE :

Fast Top-K Path-Based Relevance Query on Massive Graphs

ABSTRACT:

Getting the things highly-relevant to a given set of question things is a key task for varied applications, such as recommendation and relationship prediction. A family of path-based relevance metrics, which quantify item relevance primarily based on the ways in an item graph, have been shown to be effective in capturing the relevance in many applications. Despite their effectiveness, path-based mostly relevance normally requires time-consuming iterative computation. We propose an approach to obtain the prime-k most relevant things for a given query item set quickly. Our approach uses novel score bounds to detect the emergence of the top-k things throughout the computation. The approach is designed for a distributed environment, that makes it scale for large graphs having billions of nodes. Our experimental results show that the proposed approach can provide the results up to 2 order of magnitudes faster than previously proposed approaches and can scale well with each the size of input and the amount of machines utilized in the computation.