Virtual Web Based Personalized PageRank Updating

TL;DR

This paper introduces VWPPR, a novel method combining Virtual Web architectures with TrackingPPR and Gauss-Southwell techniques to efficiently update Personalized PageRank in large, dynamic web graphs involving node and link modifications.

Contribution

The paper presents VWPPR, a new algorithm that significantly accelerates Personalized PageRank updates in large, evolving graphs by integrating Virtual Web structures with existing updating methods.

Findings

VWPPR is 3-6 times faster than LazyForwardUpdate.

VWPPR reduces iteration counts by 4.4-10 times.

Effective on datasets with millions of nodes and links.

Abstract

Growing popularity of social networks demands a highly efficient Personalized PageRank (PPR) updating due to the fast-evolving web graphs of enormous size. While current researches are focusing on PPR updating under link structure modification, efficiently updating PPR when node insertion/ deletion involved remains a challenge. In the previous work called Virtual Web (VW), a few VW architectures are designed, which results in some highly effective initializations to significantly accelerate PageRank updating under both link modification and page insertion/deletion. In the paper, under the general scenario of link modification and node insertion/deletion we tackle the fast PPR updating problem. Specifically, we combine VW with the TrackingPPR method to generate initials, which are then used by the Gauss-Southwell method for fast PPR updating. The algorithm is named VWPPR method. In extensive experiments, three real-world datasets are used that contain 1~5.6M nodes and 6.7M~129M links, while a node perturbation of 40k and link perturbation of 1% are applied. Comparing to the more recent LazyForwardUpdate method, which handles the general PPR updating problem, the VWPPR method is 3~6 times faster in terms of running time, or 4.4~10 times faster in terms of iteration numbers.