{"id":"https://openalex.org/W4281724293","doi":"https://doi.org/10.1145/3534678.3539076","title":"Sparx: Distributed Outlier Detection at Scale","display_name":"Sparx: Distributed Outlier Detection at Scale","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4281724293","doi":"https://doi.org/10.1145/3534678.3539076"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539076","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539076","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539076","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539076","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077750725","display_name":"Sean X. Zhang","orcid":"https://orcid.org/0000-0003-1166-2563"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sean Zhang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027798802","display_name":"Varun Ursekar","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Varun Ursekar","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001634795","display_name":"Leman Akoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leman Akoglu","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077750725"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.3144,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49019504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4530","last_page":"4540"},"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":0.9853000044822693,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9682999849319458,"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":0.8106451034545898},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7138581871986389},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.683374285697937},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.5604864358901978},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.547338604927063},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.510564923286438},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5070681571960449},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.49993324279785156},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4764266908168793},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.44854798913002014},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4318939745426178},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4153633415699005},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41041263937950134},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3841959834098816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3090907335281372},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2986709475517273},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22361207008361816},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.15396583080291748}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106451034545898},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7138581871986389},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.683374285697937},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.5604864358901978},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.547338604927063},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.510564923286438},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5070681571960449},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.49993324279785156},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4764266908168793},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.44854798913002014},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4318939745426178},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4153633415699005},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41041263937950134},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3841959834098816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3090907335281372},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2986709475517273},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22361207008361816},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.15396583080291748},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3534678.3539076","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539076","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539076","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.01281","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.01281","pdf_url":"https://arxiv.org/pdf/2206.01281","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3534678.3539076","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3534678.3539076","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3534678.3539076","source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1171700966","display_name":null,"funder_award_id":"NSF CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5182979596","display_name":null,"funder_award_id":"NETCOM","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5512748762","display_name":null,"funder_award_id":"1452425","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","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"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4281724293.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1673310716","https://openalex.org/W1865797552","https://openalex.org/W1989750313","https://openalex.org/W1989870481","https://openalex.org/W2015887370","https://openalex.org/W2037757210","https://openalex.org/W2092952332","https://openalex.org/W2112657736","https://openalex.org/W2144182447","https://openalex.org/W2147717514","https://openalex.org/W2161970940","https://openalex.org/W2169900105","https://openalex.org/W2173213060","https://openalex.org/W2328192810","https://openalex.org/W2507487910","https://openalex.org/W2755997547","https://openalex.org/W2809400334","https://openalex.org/W2884123408","https://openalex.org/W2902955734","https://openalex.org/W2906931820","https://openalex.org/W3017320328","https://openalex.org/W3106312933","https://openalex.org/W3153838899"],"related_works":["https://openalex.org/W2606446052","https://openalex.org/W2036021480","https://openalex.org/W3195777957","https://openalex.org/W2382668227","https://openalex.org/W2348482143","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W3107369729"],"abstract_inverted_index":{"There":[0],"is":[1,42],"no":[2],"shortage":[3],"of":[4,16,28,49,90,94,110,126],"outlier":[5],"detection":[6],"(OD)":[7],"algorithms":[8],"in":[9,77],"the":[10,25,33,135],"literature,":[11],"yet":[12],"a":[13,21,65],"vast":[14],"body":[15],"them":[17],"are":[18],"designed":[19],"for":[20,35,52,70],"single":[22],"machine.":[23],"With":[24],"increasing":[26],"reality":[27],"already":[29],"cloud-resident":[30],"datasets":[31],"comes":[32],"need":[34],"distributed":[36],"OD":[37,67,127],"techniques.":[38],"This":[39,55],"area,":[40],"however,":[41],"not":[43],"only":[44],"understudied":[45],"but":[46],"also":[47],"short":[48],"public-domain":[50],"implementations":[51],"practical":[53,124],"use.":[54],"paper":[56],"aims":[57],"to":[58,103],"fill":[59],"this":[60],"gap:":[61],"We":[62],"design":[63],"Sparx,":[64],"data-parallel":[66],"algorithm":[68],"suitable":[69],"shared-nothing":[71],"infrastructures,":[72],"which":[73],"we":[74,96,131],"specifically":[75],"implement":[76],"Apache":[78,136],"Spark.":[79],"Through":[80],"extensive":[81],"experiments":[82],"on":[83,128],"three":[84],"real-world":[85],"datasets,":[86,130],"with":[87],"several":[88],"billions":[89],"points":[91,111],"and":[92,119],"millions":[93],"features,":[95],"show":[97],"that":[98],"existing":[99],"open-source":[100,132],"solutions":[101],"fail":[102],"scale":[104],"up;":[105],"either":[106],"by":[107],"large":[108],"number":[109],"or":[112],"high":[113],"dimensionality,":[114],"whereas":[115],"Sparx":[116,133],"yields":[117],"scalable":[118],"effective":[120],"performance.":[121],"To":[122],"facilitate":[123],"use":[125],"modern-scale":[129],"under":[134],"license":[137],"at":[138],"https://tinyurl.com/sparx2022.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}