FORA: Simple and effective approximate single-source personalized PageRank

Sibo Wang, Renchi Yang, Xiaokui Xiao, Zhewei Wei, Yin Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

Given a graph G, a source node s and a target node t, the personalized PageRank (PPR) of t with respect to s is the probability that a random walk starting from s terminates at t. A single-source PPR (SSPPR) query enumerates all nodes in G, and returns the top-k nodes with the highest PPR values with respect to a given source node s. SSPPR has important applications in web search and social networks, e.g., in Twitter's Who-To-Follow recommendation service. However, SSPPR computation is immensely expensive, and at the same time resistant to indexing and materialization. So far, existing solutions either use heuristics, which do not guarantee result quality, or rely on the strong computing power of modern data centers, which is costly. Motivated by this, we propose FORA, a simple and effective index-based solution for approximate SSPPR processing, with rigorous guarantees on result quality. The basic idea of FORA is to combine two existing methods Forward Push (which is fast but does not guarantee quality) and Monte Carlo Random Walk (accurate but slow) in a simple and yet non-trivial way, leading to an algorithm that is both fast and accurate. Further, FORA includes a simple and effective indexing scheme, as well as a module for top-k selection with high pruning power. Extensive experiments demonstrate that FORA is orders of magnitude more efficient than its main competitors. Notably, on a billion-edge Twitter dataset, FORA answers a top-500 approximate SSPPR query within 5 seconds, using a single commodity server.

Original languageEnglish
Title of host publicationKDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages505-514
Number of pages10
VolumePart F129685
ISBN (Electronic)9781450348874
DOIs
Publication statusPublished - 13 Aug 2017
Event23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017 - Halifax, Canada
Duration: 13 Aug 201717 Aug 2017

Other

Other23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017
CountryCanada
CityHalifax
Period13/8/1717/8/17

Fingerprint

Servers
Processing
Experiments

Keywords

  • Forward push
  • Personalized PageRank
  • Random walk

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Wang, S., Yang, R., Xiao, X., Wei, Z., & Yang, Y. (2017). FORA: Simple and effective approximate single-source personalized PageRank. In KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Vol. Part F129685, pp. 505-514). Association for Computing Machinery. https://doi.org/10.1145/3097983.3098072

FORA : Simple and effective approximate single-source personalized PageRank. / Wang, Sibo; Yang, Renchi; Xiao, Xiaokui; Wei, Zhewei; Yang, Yin.

KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. Part F129685 Association for Computing Machinery, 2017. p. 505-514.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, S, Yang, R, Xiao, X, Wei, Z & Yang, Y 2017, FORA: Simple and effective approximate single-source personalized PageRank. in KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. vol. Part F129685, Association for Computing Machinery, pp. 505-514, 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017, Halifax, Canada, 13/8/17. https://doi.org/10.1145/3097983.3098072
Wang S, Yang R, Xiao X, Wei Z, Yang Y. FORA: Simple and effective approximate single-source personalized PageRank. In KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. Part F129685. Association for Computing Machinery. 2017. p. 505-514 https://doi.org/10.1145/3097983.3098072
Wang, Sibo ; Yang, Renchi ; Xiao, Xiaokui ; Wei, Zhewei ; Yang, Yin. / FORA : Simple and effective approximate single-source personalized PageRank. KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. Part F129685 Association for Computing Machinery, 2017. pp. 505-514
@inproceedings{145080b6e9444de9bdf0f955ef112eb5,
title = "FORA: Simple and effective approximate single-source personalized PageRank",
abstract = "Given a graph G, a source node s and a target node t, the personalized PageRank (PPR) of t with respect to s is the probability that a random walk starting from s terminates at t. A single-source PPR (SSPPR) query enumerates all nodes in G, and returns the top-k nodes with the highest PPR values with respect to a given source node s. SSPPR has important applications in web search and social networks, e.g., in Twitter's Who-To-Follow recommendation service. However, SSPPR computation is immensely expensive, and at the same time resistant to indexing and materialization. So far, existing solutions either use heuristics, which do not guarantee result quality, or rely on the strong computing power of modern data centers, which is costly. Motivated by this, we propose FORA, a simple and effective index-based solution for approximate SSPPR processing, with rigorous guarantees on result quality. The basic idea of FORA is to combine two existing methods Forward Push (which is fast but does not guarantee quality) and Monte Carlo Random Walk (accurate but slow) in a simple and yet non-trivial way, leading to an algorithm that is both fast and accurate. Further, FORA includes a simple and effective indexing scheme, as well as a module for top-k selection with high pruning power. Extensive experiments demonstrate that FORA is orders of magnitude more efficient than its main competitors. Notably, on a billion-edge Twitter dataset, FORA answers a top-500 approximate SSPPR query within 5 seconds, using a single commodity server.",
keywords = "Forward push, Personalized PageRank, Random walk",
author = "Sibo Wang and Renchi Yang and Xiaokui Xiao and Zhewei Wei and Yin Yang",
year = "2017",
month = "8",
day = "13",
doi = "10.1145/3097983.3098072",
language = "English",
volume = "Part F129685",
pages = "505--514",
booktitle = "KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - FORA

T2 - Simple and effective approximate single-source personalized PageRank

AU - Wang, Sibo

AU - Yang, Renchi

AU - Xiao, Xiaokui

AU - Wei, Zhewei

AU - Yang, Yin

PY - 2017/8/13

Y1 - 2017/8/13

N2 - Given a graph G, a source node s and a target node t, the personalized PageRank (PPR) of t with respect to s is the probability that a random walk starting from s terminates at t. A single-source PPR (SSPPR) query enumerates all nodes in G, and returns the top-k nodes with the highest PPR values with respect to a given source node s. SSPPR has important applications in web search and social networks, e.g., in Twitter's Who-To-Follow recommendation service. However, SSPPR computation is immensely expensive, and at the same time resistant to indexing and materialization. So far, existing solutions either use heuristics, which do not guarantee result quality, or rely on the strong computing power of modern data centers, which is costly. Motivated by this, we propose FORA, a simple and effective index-based solution for approximate SSPPR processing, with rigorous guarantees on result quality. The basic idea of FORA is to combine two existing methods Forward Push (which is fast but does not guarantee quality) and Monte Carlo Random Walk (accurate but slow) in a simple and yet non-trivial way, leading to an algorithm that is both fast and accurate. Further, FORA includes a simple and effective indexing scheme, as well as a module for top-k selection with high pruning power. Extensive experiments demonstrate that FORA is orders of magnitude more efficient than its main competitors. Notably, on a billion-edge Twitter dataset, FORA answers a top-500 approximate SSPPR query within 5 seconds, using a single commodity server.

AB - Given a graph G, a source node s and a target node t, the personalized PageRank (PPR) of t with respect to s is the probability that a random walk starting from s terminates at t. A single-source PPR (SSPPR) query enumerates all nodes in G, and returns the top-k nodes with the highest PPR values with respect to a given source node s. SSPPR has important applications in web search and social networks, e.g., in Twitter's Who-To-Follow recommendation service. However, SSPPR computation is immensely expensive, and at the same time resistant to indexing and materialization. So far, existing solutions either use heuristics, which do not guarantee result quality, or rely on the strong computing power of modern data centers, which is costly. Motivated by this, we propose FORA, a simple and effective index-based solution for approximate SSPPR processing, with rigorous guarantees on result quality. The basic idea of FORA is to combine two existing methods Forward Push (which is fast but does not guarantee quality) and Monte Carlo Random Walk (accurate but slow) in a simple and yet non-trivial way, leading to an algorithm that is both fast and accurate. Further, FORA includes a simple and effective indexing scheme, as well as a module for top-k selection with high pruning power. Extensive experiments demonstrate that FORA is orders of magnitude more efficient than its main competitors. Notably, on a billion-edge Twitter dataset, FORA answers a top-500 approximate SSPPR query within 5 seconds, using a single commodity server.

KW - Forward push

KW - Personalized PageRank

KW - Random walk

UR - http://www.scopus.com/inward/record.url?scp=85029106899&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029106899&partnerID=8YFLogxK

U2 - 10.1145/3097983.3098072

DO - 10.1145/3097983.3098072

M3 - Conference contribution

AN - SCOPUS:85029106899

VL - Part F129685

SP - 505

EP - 514

BT - KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

ER -