@article{f52d2f80495e40438dbe19cdd944adb0,
title = "Locality-sensitive and Re-use Promoting Personalized PageRank computations",
abstract = "Node distance/proximity measures are used for quantifying how nearby or otherwise related two or more nodes on a graph are. In particular, personalized PageRank (PPR) based measures of node proximity have been shown to be highly effective in many prediction and recommendation applications. Despite its effectiveness, however, the use of personalized PageRank for large graphs is difficult due to its high computation cost. In this paper, we propose a Locality-sensitive, Re-use promoting, approximate Personalized PageRank (LR-PPR) algorithm for efficiently computing the PPR values relying on the localities of the given seed nodes on the graph: (a) The LR-PPR algorithm is locality sensitive in the sense that it reduces the computational cost of the PPR computation process by focusing on the local neighborhoods of the seed nodes. (b) LR-PPR is re-use promoting in that instead of performing a monolithic computation for the given seed node set using the entire graph, LR-PPR divides the work into localities of the seeds and caches the intermediary results obtained during the computation. These cached results are then reused for future queries sharing seed nodes. Experiment results for different data sets and under different scenarios show that LR-PPR algorithm is highly-efficient and accurate.",
keywords = "Locality-sensitivity, Personalized PageRank, Reuse-promotion, Scalability",
author = "Kim, {Jung Hyun} and Kasim Candan and Sapino, {Maria Luisa}",
note = "Funding Information: This work is supported by NSF Grants 1318788 {"}Data Management for Real-Time Data Driven Epidemic Spread Simulations{"} and 1339835 {"}E-SDMS: Energy Simulation Data Management System Software{"}. A preliminary version of this work appeared as [24 ]: Jung Hyun Kim, K. Sel{\~A}§uk Candan, and Maria Luisa Sapino. LR-PPR: Locality-Sensitive, Re-use Promoting, Approximate Personalized PageRank Computation. ACM International Conference on Information and Knowledge Management (CIKM'13), October 2013. We especially thank Leonardo Allisio and Ilario Dal Grande for their feedback and corrections on the manuscript and authors of Maehara et al. [29 ] for sharing with us their source code for the preprocessing stage of their algorithm. Funding Information: This work is supported by NSF Grants 1318788 “Data Management for Real-Time Data Driven Epidemic Spread Simulations” and 1339835 “E-SDMS: Energy Simulation Data Management System Software”. A preliminary version of this work appeared as []: Jung Hyun Kim, K. Sel{\c c}uk Candan, and Maria Luisa Sapino. LR-PPR: Locality-Sensitive, Re-use Promoting, Approximate Personalized PageRank Computation. ACM International Conference on Information and Knowledge Management (CIKM{\textquoteright}13), October 2013. We especially thank Leonardo Allisio and Ilario Dal Grande for their feedback and corrections on the manuscript and authors of Maehara et al. [] for sharing with us their source code for the preprocessing stage of their algorithm. Publisher Copyright: {\textcopyright} 2015, Springer-Verlag London.",
year = "2016",
month = may,
day = "1",
doi = "10.1007/s10115-015-0843-6",
language = "English (US)",
volume = "47",
pages = "261--299",
journal = "Knowledge and Information Systems",
issn = "0219-1377",
publisher = "Springer London",
number = "2",
}