{"id":"https://openalex.org/W2020594369","doi":"https://doi.org/10.1145/1871437.1871501","title":"Set cover algorithms for very large datasets","display_name":"Set cover algorithms for very large datasets","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2020594369","doi":"https://doi.org/10.1145/1871437.1871501","mag":"2020594369"},"language":"en","primary_location":{"id":"doi:10.1145/1871437.1871501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","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/A5031896681","display_name":"Graham Cormode","orcid":"https://orcid.org/0000-0002-0698-0922"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Graham Cormode","raw_affiliation_strings":["AT&T Labs - Research, Florham Park, NJ, USA","AT&T Labs---Research, Florham Park, NJ, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"AT&T Labs - Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs---Research, Florham Park, NJ, USA#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087578885","display_name":"Howard Karloff","orcid":"https://orcid.org/0000-0003-4490-2324"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Howard Karloff","raw_affiliation_strings":["AT&T Labs - Research, Florham Park, NJ, USA","AT&T Labs---Research, Florham Park, NJ, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"AT&T Labs - Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs---Research, Florham Park, NJ, USA#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087794199","display_name":"Anthony Wirth","orcid":"https://orcid.org/0000-0003-3746-6704"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Anthony Wirth","raw_affiliation_strings":["The University of Melbourne, Parkville, Australia","(The University of Melbourne, Parkville, Australia)"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Parkville, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"(The University of Melbourne, Parkville, Australia)","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031896681"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":3.7586,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.93005363,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"479","last_page":"488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10374","display_name":"Advanced Graph Theory Research","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/cover","display_name":"Cover (algebra)","score":0.6771736145019531},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6556349396705627},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5029510855674744},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4365540146827698},{"id":"https://openalex.org/keywords/set-cover-problem","display_name":"Set cover problem","score":0.42626211047172546},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07607224583625793},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06669104099273682}],"concepts":[{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.6771736145019531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6556349396705627},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5029510855674744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4365540146827698},{"id":"https://openalex.org/C100808899","wikidata":"https://www.wikidata.org/wiki/Q1192100","display_name":"Set cover problem","level":3,"score":0.42626211047172546},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07607224583625793},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06669104099273682},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1871437.1871501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.190.6477","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.190.6477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/people/Cormode_Graham/library/publications/CormodeKarloffWirth10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W112063162","https://openalex.org/W172108465","https://openalex.org/W1535804456","https://openalex.org/W1554813885","https://openalex.org/W1979943645","https://openalex.org/W1993284846","https://openalex.org/W2040924621","https://openalex.org/W2055687752","https://openalex.org/W2064209160","https://openalex.org/W2133409729","https://openalex.org/W2143996311","https://openalex.org/W2144970024","https://openalex.org/W2148372359","https://openalex.org/W4285719527","https://openalex.org/W6606993022","https://openalex.org/W7014757045"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2035485837","https://openalex.org/W3145090562","https://openalex.org/W3165916245","https://openalex.org/W2003676461","https://openalex.org/W2026615147","https://openalex.org/W2007865068"],"abstract_inverted_index":{"The":[0,100],"problem":[1],"of":[2,9,18,30,69,81,144],"Set":[3,124],"Cover\u2014to":[4],"find":[5],"the":[6,16,50,70,75,78,92],"smallest":[7],"subcollection":[8],"sets":[10],"that":[11,60,138,143],"covers":[12],"some":[13],"universe\u2014is":[14],"at":[15,84],"heart":[17],"many":[19,105],"data":[20,38,41],"and":[21,40,56,97,113,169],"analysis":[22],"tasks.":[23],"It":[24],"arises":[25],"in":[26,115,164],"a":[27,66,131,136,161],"wide":[28],"range":[29],"settings,":[31],"including":[32],"operations":[33],"research,":[34],"machine":[35],"learning,":[36],"planning,":[37],"quality":[39],"mining.":[42],"Although":[43],"finding":[44],"an":[45,170],"optimal":[46],"solution":[47,137],"is":[48,53,94,139,148],"NP-hard,":[49],"greedy":[51,71,101],"algorithm":[52,102,133],"widely":[54],"used,":[55],"typically":[57],"finds":[58,135],"solutions":[59],"are":[61,111],"close":[62,141],"to":[63,108,117,122,126,142,152],"optimal.":[64],"However,":[65],"direct":[67],"implementation":[68],"approach,":[72],"which":[73,110,134,147],"picks":[74],"set":[76],"with":[77],"largest":[79],"number":[80],"uncovered":[82],"items":[83],"each":[85],"step,":[86],"does":[87],"not":[88],"behave":[89],"well":[90],"when":[91],"input":[93],"very":[95],"large":[96,127],"disk":[98,156],"resident.":[99],"must":[103],"make":[104],"random":[106],"accesses":[107],"disk,":[109],"unpredictable":[112],"costly":[114],"comparison":[116],"linear":[118],"scans.":[119],"In":[120],"order":[121],"scale":[123],"Cover":[125],"datasets,":[128,168],"we":[129],"provide":[130],"new":[132],"provably":[140],"greedy,":[145],"but":[146],"much":[149],"more":[150],"efficient":[151],"implement":[153],"using":[154],"modern":[155],"technology.":[157],"Our":[158],"experiments":[159],"show":[160],"ten-fold":[162],"improvement":[163,173],"speed":[165],"on":[166,174],"moderately-sized":[167],"even":[171],"greater":[172],"larger":[175],"datasets.":[176]},"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":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}