TPA: Fast, Scalable, and Accurate Method for Approximate Random Walk with Restart on Billion Scale Graphs

TL;DR

TPA is a novel method that efficiently computes approximate random walk with restart on billion-scale graphs, offering significant improvements in speed and memory usage while maintaining high accuracy for various data mining tasks.

Contribution

The paper introduces TPA, a new scalable approach that divides the RWR approximation into neighbor and stranger components, enhancing speed and accuracy on large graphs.

Findings

TPA reduces preprocessing time by up to 3.5x compared to state-of-the-art methods.

TPA achieves up to 30x faster online RWR computation while maintaining high accuracy.

TPA uses properties of real-world graphs to improve approximation quality and scalability.

Abstract

Given a large graph, how can we determine similarity between nodes in a fast and accurate way? Random walk with restart (RWR) is a popular measure for this purpose and has been exploited in numerous data mining applications including ranking, anomaly detection, link prediction, and community detection. However, previous methods for computing exact RWR require prohibitive storage sizes and computational costs, and alternative methods which avoid such costs by computing approximate RWR have limited accuracy. In this paper, we propose TPA, a fast, scalable, and highly accurate method for computing approximate RWR on large graphs. TPA exploits two important properties in RWR: 1) nodes close to a seed node are likely to be revisited in following steps due to block-wise structure of many real-world graphs, and 2) RWR scores of nodes which reside far from the seed node are proportional to their PageRank scores. Based on these two properties, TPA divides approximate RWR problem into two subproblems called neighbor approximation and stranger approximation. In the neighbor approximation, TPA estimates RWR scores of nodes close to the seed based on scores of few early steps from the seed. In the stranger approximation, TPA estimates RWR scores for nodes far from the seed using their PageRank. The stranger and neighbor approximations are conducted in the preprocessing phase and the online phase, respectively. Through extensive experiments, we show that TPA requires up to 3.5x less time with up to 40x less memory space than other state-of-the-art methods for the preprocessing phase. In the online phase, TPA computes approximate RWR up to 30x faster than existing methods while maintaining high accuracy.