{"id":"https://openalex.org/W2743479942","doi":"https://doi.org/10.1145/3097983.3098179","title":"Distributed Local Outlier Detection in Big Data","display_name":"Distributed Local Outlier Detection in Big Data","publication_year":2017,"publication_date":"2017-08-04","ids":{"openalex":"https://openalex.org/W2743479942","doi":"https://doi.org/10.1145/3097983.3098179","mag":"2743479942"},"language":"en","primary_location":{"id":"doi:10.1145/3097983.3098179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3097983.3098179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108577922","display_name":"Yizhou Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yizhou Yan","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049926126","display_name":"Lei Cao","orcid":"https://orcid.org/0000-0001-9909-8607"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Cao","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058747551","display_name":"Caitlin Kulhman","orcid":null},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caitlin Kulhman","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008269094","display_name":"Elke A. Rundensteiner","orcid":"https://orcid.org/0000-0001-5375-9254"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elke Rundensteiner","raw_affiliation_strings":["Worcester Polytechnic Institute, Worcester, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, Worcester, MA, USA","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108577922"],"corresponding_institution_ids":["https://openalex.org/I107077323"],"apc_list":null,"apc_paid":null,"fwci":5.2014,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96344447,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1225","last_page":"1234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11220","display_name":"Water Systems and Optimization","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10400","display_name":"Network Security and Intrusion Detection","score":0.9754999876022339,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8781811594963074},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7058495879173279},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6875095367431641},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6279041767120361},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.5753426551818848},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5691834688186646},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5523699522018433},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5519345998764038},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4981248378753662},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.48686450719833374},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41625383496284485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27445030212402344},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20217493176460266},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1622319519519806}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8781811594963074},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7058495879173279},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6875095367431641},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6279041767120361},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.5753426551818848},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5691834688186646},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5523699522018433},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5519345998764038},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4981248378753662},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.48686450719833374},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41625383496284485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27445030212402344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20217493176460266},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1622319519519806},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3097983.3098179","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3097983.3098179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6299999952316284,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G8106998152","display_name":null,"funder_award_id":"1305258","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W42722137","https://openalex.org/W1552339598","https://openalex.org/W1989750313","https://openalex.org/W1989870481","https://openalex.org/W2049003051","https://openalex.org/W2049058890","https://openalex.org/W2061051181","https://openalex.org/W2066219179","https://openalex.org/W2115583184","https://openalex.org/W2124536999","https://openalex.org/W2129281431","https://openalex.org/W2130305366","https://openalex.org/W2131975293","https://openalex.org/W2144182447","https://openalex.org/W2154879298","https://openalex.org/W2169900105","https://openalex.org/W2173213060","https://openalex.org/W2211491388","https://openalex.org/W2338990760","https://openalex.org/W3099369182","https://openalex.org/W4245050711","https://openalex.org/W4253461361","https://openalex.org/W4254182148"],"related_works":["https://openalex.org/W2936171637","https://openalex.org/W1586214342","https://openalex.org/W2499612753","https://openalex.org/W2260589296","https://openalex.org/W3157828377","https://openalex.org/W3111802945","https://openalex.org/W181157820","https://openalex.org/W3137329302","https://openalex.org/W4241817935","https://openalex.org/W2937168573"],"abstract_inverted_index":{"In":[0],"this":[1,142],"work,":[2],"we":[3,107,151],"present":[4],"the":[5,10,54,57,66,87,124,129,136,145,164,179,183,187,201],"first":[6],"distributed":[7,44,78,95],"solution":[8,75],"for":[9,27,102],"Local":[11],"Outlier":[12],"Factor":[13],"(LOF)":[14],"method":[15],"--":[16],"a":[17,61,77,93,109,153],"popular":[18],"outlier":[19],"detection":[20],"technique":[21],"shown":[22],"to":[23,53,65,208],"be":[24],"very":[25],"effective":[26],"datasets":[28,33,199],"with":[29],"skewed":[30],"distributions.":[31],"As":[32],"increase":[34],"radically":[35],"in":[36,92,120,144],"size,":[37],"highly":[38],"scalable":[39],"LOF":[40,58,79,88,125,180],"algorithms":[41],"leveraging":[42,98],"modern":[43],"infrastructures":[45],"are":[46],"required.":[47],"This":[48],"poses":[49],"significant":[50],"challenges":[51],"due":[52],"complexity":[55],"of":[56,63,86,123,131,147,155,186,205],"definition,":[59],"and":[60,197,203],"lack":[62],"access":[64],"entire":[67],"dataset":[68],"at":[69],"any":[70],"individual":[71],"compute":[72],"machine.":[73],"Our":[74,190],"features":[76],"pipeline":[80],"framework,":[81],"called":[82],"DLOF.":[83],"Each":[84],"stage":[85],"computation":[89,165,181],"is":[90,118],"conducted":[91],"fully":[94],"fashion":[96],"by":[97,176],"our":[99,206],"invariant":[100],"observation":[101],"intermediate":[103],"value":[104],"management.":[105],"Furthermore,":[106],"propose":[108],"data":[110,132],"assignment":[111],"strategy":[112,143],"which":[113],"ensures":[114],"that":[115],"each":[116,168],"machine":[117],"self-sufficient":[119],"all":[121],"stages":[122,185],"pipeline,":[126],"while":[127],"minimizing":[128],"number":[130,154],"replicas.":[133],"Based":[134],"on":[135],"convergence":[137],"property":[138],"derived":[139],"from":[140],"analyzing":[141],"context":[146],"real":[148,196],"world":[149],"datasets,":[150],"introduce":[152],"data-driven":[156],"optimization":[157],"strategies.":[158],"These":[159],"strategies":[160],"not":[161],"only":[162],"minimize":[163],"costs":[166,175],"within":[167],"stage,":[169],"but":[170],"also":[171],"eliminate":[172],"unnecessary":[173],"communication":[174],"aggressively":[177],"pushing":[178],"into":[182],"early":[184],"DLOF":[188],"pipeline.":[189],"comprehensive":[191],"experimental":[192],"study":[193],"using":[194],"both":[195],"synthetic":[198],"confirms":[200],"efficiency":[202],"scalability":[204],"approach":[207],"terabyte":[209],"level":[210],"data.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}