{"id":"https://openalex.org/W2041559880","doi":"https://doi.org/10.1145/2339530.2339669","title":"A near-linear time approximation algorithm for angle-based outlier detection in high-dimensional data","display_name":"A near-linear time approximation algorithm for angle-based outlier detection in high-dimensional data","publication_year":2012,"publication_date":"2012-08-12","ids":{"openalex":"https://openalex.org/W2041559880","doi":"https://doi.org/10.1145/2339530.2339669","mag":"2041559880"},"language":"en","primary_location":{"id":"doi:10.1145/2339530.2339669","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2339530.2339669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5069747496","display_name":"Ninh Pham","orcid":"https://orcid.org/0000-0001-5768-9900"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ninh Pham","raw_affiliation_strings":["IT University of Copenhagen, Copenhagen, Denmark","It university of copenhagen, copenhagen, denmark#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]},{"raw_affiliation_string":"It university of copenhagen, copenhagen, denmark#TAB#","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014293815","display_name":"Rasmus Pagh","orcid":"https://orcid.org/0000-0002-1516-9306"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Rasmus Pagh","raw_affiliation_strings":["IT University of Copenhagen, Copenhagen, Denmark","It university of copenhagen, copenhagen, denmark#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]},{"raw_affiliation_string":"It university of copenhagen, copenhagen, denmark#TAB#","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I83467386"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":116,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"877","last_page":"885"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.982699990272522,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9570000171661377,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7276037931442261},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6142066717147827},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6137806177139282},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.576528012752533},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5715954303741455},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5582756996154785},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5486598014831543},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5338191986083984},{"id":"https://openalex.org/keywords/random-projection","display_name":"Random projection","score":0.48446154594421387},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4728158712387085},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.4392612874507904},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.4344022572040558},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.42992645502090454},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4116944670677185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20100194215774536},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.08060327172279358}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7276037931442261},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6142066717147827},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6137806177139282},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.576528012752533},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5715954303741455},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5582756996154785},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5486598014831543},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5338191986083984},{"id":"https://openalex.org/C2777036070","wikidata":"https://www.wikidata.org/wiki/Q18393452","display_name":"Random projection","level":2,"score":0.48446154594421387},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4728158712387085},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.4392612874507904},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.4344022572040558},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.42992645502090454},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4116944670677185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20100194215774536},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.08060327172279358},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2339530.2339669","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2339530.2339669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/eacbd5ca-09d5-4087-8c8b-e4b0b7596088","is_oa":false,"landing_page_url":"https://pure.itu.dk/portal/da/publications/eacbd5ca-09d5-4087-8c8b-e4b0b7596088","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pham, N D & Pagh, R 2012, A Near-linear Time Approximation Algorithm for Angle-based Outlier Detection in High-dimensional Data. in KDD '12 Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining . Association for Computing Machinery, pp. 877-885. < http://dl.acm.org/citation.cfm?id=2339669 >","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.718.3868","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.718.3868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.itu.dk/people/ndap/FastVOA.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W199035648","https://openalex.org/W1552339598","https://openalex.org/W1795239726","https://openalex.org/W1980389212","https://openalex.org/W1985123706","https://openalex.org/W1986332411","https://openalex.org/W1989274820","https://openalex.org/W2012833704","https://openalex.org/W2061122559","https://openalex.org/W2080745194","https://openalex.org/W2096552750","https://openalex.org/W2097017789","https://openalex.org/W2110784166","https://openalex.org/W2122361470","https://openalex.org/W2124536999","https://openalex.org/W2129281431","https://openalex.org/W2144182447","https://openalex.org/W2148373332","https://openalex.org/W2165533158","https://openalex.org/W2166377520","https://openalex.org/W3120740533","https://openalex.org/W4253461361","https://openalex.org/W4254182148"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2132433561","https://openalex.org/W3080558755","https://openalex.org/W2952300832","https://openalex.org/W2541308381","https://openalex.org/W4389650053"],"abstract_inverted_index":{"Outlier":[0],"mining":[1,13,71],"in":[2,25,48,70,78,106,109,123],"d-dimensional":[3],"point":[4],"sets":[5,158],"is":[6,33,94,118,163],"a":[7,82,88,128,133],"fundamental":[8],"and":[9,154,165],"well":[10],"studied":[11],"data":[12,104,157,171],"task":[14],"due":[15],"to":[16,96,120,126,141,167],"its":[17],"variety":[18],"of":[19,30,41,56,66,112,136,139,145],"applications.":[20],"Most":[21],"such":[22],"applications":[23],"arise":[24],"high-dimensional":[26,49,72,170],"domains.":[27],"A":[28],"bottleneck":[29],"existing":[31],"approaches":[32],"that":[34,93,160],"implicit":[35],"or":[36,43],"explicit":[37],"assessments":[38],"on":[39,53,152],"concepts":[40],"distance":[42],"nearest":[44],"neighbor":[45],"are":[46],"deteriorated":[47],"data.":[50,114],"Following":[51],"up":[52],"the":[54,64,98,110,113,137,143],"work":[55],"Kriegel":[57],"et":[58],"al.":[59],"(KDD":[60],"'08),":[61],"we":[62,86],"investigate":[63],"use":[65],"angle-based":[67,99],"outlier":[68,100],"factor":[69,101],"outliers.":[73],"While":[74],"their":[75],"algorithm":[76],"runs":[77],"cubic":[79],"time":[80,84,107],"(with":[81],"quadratic":[83],"heuristic),":[85],"propose":[87],"novel":[89],"random":[90],"projection-based":[91],"technique":[92],"able":[95],"estimate":[97],"for":[102],"all":[103],"points":[105],"near-linear":[108],"size":[111],"Also,":[115],"our":[116,146,161],"approach":[117,162],"suitable":[119],"be":[121],"performed":[122],"parallel":[124,129],"environment":[125],"achieve":[127],"speedup.":[130],"We":[131],"introduce":[132],"theoretical":[134],"analysis":[135],"quality":[138],"approximation":[140],"guarantee":[142],"reliability":[144],"estimation":[147],"algorithm.":[148],"The":[149],"empirical":[150],"experiments":[151],"synthetic":[153],"real":[155],"world":[156],"demonstrate":[159],"efficient":[164],"scalable":[166],"very":[168],"large":[169],"sets.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}