ALID: Scalable dominant cluster detection

Lingyang Chu, Shuhui Wang, Siyuan Liu, Qingming Huang, Jian Pei

Research output: Contribution to journalConference article

9 Citations (Scopus)

Abstract

Detecting dominant clusters is important in many analytic applications. The state-of-the-art methods find dense subgraphs on the affinity graph as dominant clusters. However, the time and space complexities of those methods are dominated by the construction of affinity graph, which is quadratic with respect to the number of data points, and thus are impractical on large data sets. To tackle the challenge, in this paper, we apply Evolutionary Game Theory (EGT) and develop a scalable algorithm, Approximate Localized Infection Immunization Dynamics (ALID). The major idea is to perform Localized Infection Immunization Dynamics (LID) to find dense subgraphs within local ranges of the affinity graph. LID is further scaled up with guaranteed high efficiency and detection quality by an estimated Region of Interest (ROI) and a Candidate Infective Vertex Search method (CIVS). ALID only constructs small local affinity graphs and has time complexity O(C(a*+ δ)n) and space complexity O(a*(a*+δ)), where a*is the size of the largest dominant cluster, and C < n and δ < n are small constants. We demonstrate by extensive experiments on both synthetic data and real world data that ALID achieves the state-of-theart detection quality with much lower time and space cost on single machine. We also demonstrate the encouraging parallelization performance of ALID by implementing the Parallel ALID (PALID) on Apache Spark. PALID processes 50 million SIFT data points in 2.29 hours, achieving a speedup ratio of 7.51 with 8 executors.

Original languageEnglish (US)
Pages (from-to)826-837
Number of pages12
JournalProceedings of the VLDB Endowment
Volume8
Issue number8
StatePublished - Jan 1 2015
Event41st International Conference on Very Large Data Bases, VLDB 2015 - Kohala Coast, United States
Duration: Aug 31 2015Sep 4 2015

Fingerprint

Immunization
Game theory
Electric sparks

All Science Journal Classification (ASJC) codes

  • Computer Science (miscellaneous)
  • Computer Science(all)

Cite this

Chu, L., Wang, S., Liu, S., Huang, Q., & Pei, J. (2015). ALID: Scalable dominant cluster detection. Proceedings of the VLDB Endowment, 8(8), 826-837.
Chu, Lingyang ; Wang, Shuhui ; Liu, Siyuan ; Huang, Qingming ; Pei, Jian. / ALID : Scalable dominant cluster detection. In: Proceedings of the VLDB Endowment. 2015 ; Vol. 8, No. 8. pp. 826-837.
@article{3dca77fcac4841ff8f160195a1904d8b,
title = "ALID: Scalable dominant cluster detection",
abstract = "Detecting dominant clusters is important in many analytic applications. The state-of-the-art methods find dense subgraphs on the affinity graph as dominant clusters. However, the time and space complexities of those methods are dominated by the construction of affinity graph, which is quadratic with respect to the number of data points, and thus are impractical on large data sets. To tackle the challenge, in this paper, we apply Evolutionary Game Theory (EGT) and develop a scalable algorithm, Approximate Localized Infection Immunization Dynamics (ALID). The major idea is to perform Localized Infection Immunization Dynamics (LID) to find dense subgraphs within local ranges of the affinity graph. LID is further scaled up with guaranteed high efficiency and detection quality by an estimated Region of Interest (ROI) and a Candidate Infective Vertex Search method (CIVS). ALID only constructs small local affinity graphs and has time complexity O(C(a*+ δ)n) and space complexity O(a*(a*+δ)), where a*is the size of the largest dominant cluster, and C < n and δ < n are small constants. We demonstrate by extensive experiments on both synthetic data and real world data that ALID achieves the state-of-theart detection quality with much lower time and space cost on single machine. We also demonstrate the encouraging parallelization performance of ALID by implementing the Parallel ALID (PALID) on Apache Spark. PALID processes 50 million SIFT data points in 2.29 hours, achieving a speedup ratio of 7.51 with 8 executors.",
author = "Lingyang Chu and Shuhui Wang and Siyuan Liu and Qingming Huang and Jian Pei",
year = "2015",
month = "1",
day = "1",
language = "English (US)",
volume = "8",
pages = "826--837",
journal = "Proceedings of the VLDB Endowment",
issn = "2150-8097",
publisher = "Very Large Data Base Endowment Inc.",
number = "8",

}

Chu, L, Wang, S, Liu, S, Huang, Q & Pei, J 2015, 'ALID: Scalable dominant cluster detection', Proceedings of the VLDB Endowment, vol. 8, no. 8, pp. 826-837.

ALID : Scalable dominant cluster detection. / Chu, Lingyang; Wang, Shuhui; Liu, Siyuan; Huang, Qingming; Pei, Jian.

In: Proceedings of the VLDB Endowment, Vol. 8, No. 8, 01.01.2015, p. 826-837.

Research output: Contribution to journalConference article

TY - JOUR

T1 - ALID

T2 - Scalable dominant cluster detection

AU - Chu, Lingyang

AU - Wang, Shuhui

AU - Liu, Siyuan

AU - Huang, Qingming

AU - Pei, Jian

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Detecting dominant clusters is important in many analytic applications. The state-of-the-art methods find dense subgraphs on the affinity graph as dominant clusters. However, the time and space complexities of those methods are dominated by the construction of affinity graph, which is quadratic with respect to the number of data points, and thus are impractical on large data sets. To tackle the challenge, in this paper, we apply Evolutionary Game Theory (EGT) and develop a scalable algorithm, Approximate Localized Infection Immunization Dynamics (ALID). The major idea is to perform Localized Infection Immunization Dynamics (LID) to find dense subgraphs within local ranges of the affinity graph. LID is further scaled up with guaranteed high efficiency and detection quality by an estimated Region of Interest (ROI) and a Candidate Infective Vertex Search method (CIVS). ALID only constructs small local affinity graphs and has time complexity O(C(a*+ δ)n) and space complexity O(a*(a*+δ)), where a*is the size of the largest dominant cluster, and C < n and δ < n are small constants. We demonstrate by extensive experiments on both synthetic data and real world data that ALID achieves the state-of-theart detection quality with much lower time and space cost on single machine. We also demonstrate the encouraging parallelization performance of ALID by implementing the Parallel ALID (PALID) on Apache Spark. PALID processes 50 million SIFT data points in 2.29 hours, achieving a speedup ratio of 7.51 with 8 executors.

AB - Detecting dominant clusters is important in many analytic applications. The state-of-the-art methods find dense subgraphs on the affinity graph as dominant clusters. However, the time and space complexities of those methods are dominated by the construction of affinity graph, which is quadratic with respect to the number of data points, and thus are impractical on large data sets. To tackle the challenge, in this paper, we apply Evolutionary Game Theory (EGT) and develop a scalable algorithm, Approximate Localized Infection Immunization Dynamics (ALID). The major idea is to perform Localized Infection Immunization Dynamics (LID) to find dense subgraphs within local ranges of the affinity graph. LID is further scaled up with guaranteed high efficiency and detection quality by an estimated Region of Interest (ROI) and a Candidate Infective Vertex Search method (CIVS). ALID only constructs small local affinity graphs and has time complexity O(C(a*+ δ)n) and space complexity O(a*(a*+δ)), where a*is the size of the largest dominant cluster, and C < n and δ < n are small constants. We demonstrate by extensive experiments on both synthetic data and real world data that ALID achieves the state-of-theart detection quality with much lower time and space cost on single machine. We also demonstrate the encouraging parallelization performance of ALID by implementing the Parallel ALID (PALID) on Apache Spark. PALID processes 50 million SIFT data points in 2.29 hours, achieving a speedup ratio of 7.51 with 8 executors.

UR - http://www.scopus.com/inward/record.url?scp=84985005010&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84985005010&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84985005010

VL - 8

SP - 826

EP - 837

JO - Proceedings of the VLDB Endowment

JF - Proceedings of the VLDB Endowment

SN - 2150-8097

IS - 8

ER -

Chu L, Wang S, Liu S, Huang Q, Pei J. ALID: Scalable dominant cluster detection. Proceedings of the VLDB Endowment. 2015 Jan 1;8(8):826-837.