Fast, Accurate, and Flexible Algorithms for Dense Subtensor Mining

Cited 9 time in webofscience Cited 0 time in scopus
  • Hit : 382
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorShin, Kijungko
dc.contributor.authorHooi, Bryanko
dc.contributor.authorFaloutsos, Christosko
dc.date.accessioned2019-03-04T10:55:40Z-
dc.date.available2019-03-04T10:55:40Z-
dc.date.created2019-03-04-
dc.date.created2019-03-04-
dc.date.issued2018-04-
dc.identifier.citationACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, v.12, no.3-
dc.identifier.issn1556-4681-
dc.identifier.urihttp://hdl.handle.net/10203/250512-
dc.description.abstractGiven a large-scale and high-order tensor, how can we detect dense subtensors in it? Can we spot them in near-linear time but with quality guarantees? Extensive previous work has shown that dense subtensors, as well as dense subgraphs, indicate anomalous or fraudulent behavior (e.g., lockstep behavior in social networks). However, available algorithms for detecting dense subtensors are not satisfactory in terms of speed, accuracy, and flexibility. In this work, we propose two algorithms, called M-Zoom and M-Biz, for fast and accurate dense-subtensor detection with various density measures. M-Zoom gives a lower bound on the density of detected subtensors, while M-Biz guarantees the local optimality of detected subtensors. M-Zoom and M-Biz can be combined, giving the following advantages: (1) Scalable: scale near-linearly with all aspects of tensors and are up to 114x faster than state-of-the-art methods with similar accuracy, (2) Provably accurate provide a guarantee on the lowest density and local optimality of the subtensors they find, (3) Flexible: support multi-subtensor detection and size bounds as well as diverse density measures, and (4) Effective: successfully detected edit wars and bot activities in Wikipedia, and spotted network attacks from a TCP dump with near-perfect accuracy (AUC = 0.98).-
dc.languageEnglish-
dc.publisherASSOC COMPUTING MACHINERY-
dc.titleFast, Accurate, and Flexible Algorithms for Dense Subtensor Mining-
dc.typeArticle-
dc.identifier.wosid000431790300003-
dc.identifier.scopusid2-s2.0-85042545195-
dc.type.rimsART-
dc.citation.volume12-
dc.citation.issue3-
dc.citation.publicationnameACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA-
dc.identifier.doi10.1145/3154414-
dc.contributor.localauthorShin, Kijung-
dc.contributor.nonIdAuthorHooi, Bryan-
dc.contributor.nonIdAuthorFaloutsos, Christos-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorTensor-
dc.subject.keywordAuthordense subtensor-
dc.subject.keywordAuthoranomaly detection-
dc.subject.keywordAuthorfraud detection-
Appears in Collection
AI-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 9 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0