{"id":"https://openalex.org/W2035836267","doi":"https://doi.org/10.1145/2623330.2623743","title":"Correlation clustering in MapReduce","display_name":"Correlation clustering in MapReduce","publication_year":2014,"publication_date":"2014-08-22","ids":{"openalex":"https://openalex.org/W2035836267","doi":"https://doi.org/10.1145/2623330.2623743","mag":"2035836267"},"language":"en","primary_location":{"id":"doi:10.1145/2623330.2623743","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th 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/A5078401676","display_name":"Flavio Chierichetti","orcid":"https://orcid.org/0000-0001-8261-9058"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Flavio Chierichetti","raw_affiliation_strings":["Sapienza University, Rome, Italy","Sapienza University, Rome, Italy;"],"affiliations":[{"raw_affiliation_string":"Sapienza University, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Sapienza University, Rome, Italy;","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081323769","display_name":"Nilesh Dalvi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nilesh Dalvi","raw_affiliation_strings":["Trooly Inc., Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Trooly Inc., Mountain View, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101772779","display_name":"Ravi Kumar","orcid":"https://orcid.org/0000-0002-2203-2586"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi Kumar","raw_affiliation_strings":["Google Inc., Mountain View, USA","Google Inc. , Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc. , Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078401676"],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":10.9195,"has_fulltext":false,"cited_by_count":69,"citation_normalized_percentile":{"value":0.98416244,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"641","last_page":"650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8121941089630127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7793091535568237},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6815512180328369},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.647089421749115},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5363581776618958},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5338757038116455},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5028979182243347},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5022950172424316},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48161619901657104},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.45936909317970276},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.403093159198761},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3365371823310852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18587803840637207},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14801448583602905},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08218583464622498}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8121941089630127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7793091535568237},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6815512180328369},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.647089421749115},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5363581776618958},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5338757038116455},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5028979182243347},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5022950172424316},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48161619901657104},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.45936909317970276},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.403093159198761},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3365371823310852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18587803840637207},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14801448583602905},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08218583464622498},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2623330.2623743","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/650417","is_oa":false,"landing_page_url":"http://hdl.handle.net/11573/650417","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1581262234","https://openalex.org/W1978658266","https://openalex.org/W1985875030","https://openalex.org/W2020254000","https://openalex.org/W2038205067","https://openalex.org/W2048044409","https://openalex.org/W2051109346","https://openalex.org/W2051586153","https://openalex.org/W2071114738","https://openalex.org/W2071234528","https://openalex.org/W2073415627","https://openalex.org/W2079361215","https://openalex.org/W2080745194","https://openalex.org/W2087187685","https://openalex.org/W2091858563","https://openalex.org/W2097186564","https://openalex.org/W2108399535","https://openalex.org/W2108991785","https://openalex.org/W2110814195","https://openalex.org/W2116440993","https://openalex.org/W2121516976","https://openalex.org/W2141985162","https://openalex.org/W2142517301","https://openalex.org/W2148372359","https://openalex.org/W2148524305","https://openalex.org/W2149029960","https://openalex.org/W2150560146","https://openalex.org/W2153977620","https://openalex.org/W2158345769","https://openalex.org/W2164625277","https://openalex.org/W2170616854","https://openalex.org/W2171179180","https://openalex.org/W2173213060","https://openalex.org/W2295256067","https://openalex.org/W2341465005","https://openalex.org/W2914959486","https://openalex.org/W2963798309","https://openalex.org/W4235946010","https://openalex.org/W6676847830"],"related_works":["https://openalex.org/W2491448268","https://openalex.org/W2559422900","https://openalex.org/W2892323093","https://openalex.org/W3144143113","https://openalex.org/W2394193399","https://openalex.org/W2181939267","https://openalex.org/W2390610678","https://openalex.org/W3071522575","https://openalex.org/W2363054820","https://openalex.org/W2101174895"],"abstract_inverted_index":{"Correlation":[0],"clustering":[1,24],"is":[2,56],"a":[3,27,48,70],"basic":[4],"primitive":[5],"in":[6,22,59,69],"data":[7,105],"miner's":[8],"toolkit":[9],"with":[10,29],"applications":[11],"ranging":[12],"from":[13],"entity":[14],"matching":[15],"to":[16,37,86,104],"social":[17],"network":[18],"analysis.":[19],"The":[20],"goal":[21],"correlation":[23,52,89],"is,":[25],"given":[26],"graph":[28],"signed":[30],"edges,":[31],"partition":[32],"the":[33,39,87,96],"nodes":[34],"into":[35],"clusters":[36],"minimize":[38],"number":[40,72],"of":[41,73,98],"disagreements.":[42],"In":[43,75],"this":[44],"paper":[45],"we":[46,77],"obtain":[47],"new":[49],"algorithm":[50,55,81,100],"for":[51],"clustering.":[53,90],"Our":[54],"easily":[57],"implementable":[58],"computational":[60],"models":[61],"such":[62],"as":[63],"MapReduce":[64],"and":[65,67,101],"streaming,":[66],"runs":[68],"small":[71],"rounds.":[74],"addition,":[76],"show":[78],"that":[79],"our":[80,99],"obtains":[82],"an":[83],"almost":[84],"3-approximation":[85],"optimal":[88],"Experiments":[91],"on":[92],"huge":[93],"graphs":[94],"demonstrate":[95],"scalability":[97],"its":[102],"applicability":[103],"mining":[106],"problems.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":2}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}