{"id":"https://openalex.org/W2139874739","doi":"https://doi.org/10.1145/2463676.2465285","title":"Mind the gap","display_name":"Mind the gap","publication_year":2013,"publication_date":"2013-06-22","ids":{"openalex":"https://openalex.org/W2139874739","doi":"https://doi.org/10.1145/2463676.2465285","mag":"2139874739"},"language":"en","primary_location":{"id":"doi:10.1145/2463676.2465285","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2463676.2465285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data","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/A5088973453","display_name":"Iris Miliaraki","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Iris Miliaraki","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039440854","display_name":"Klaus Berberich","orcid":"https://orcid.org/0000-0003-3813-9721"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Berberich","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041227178","display_name":"Rainer Gemulla","orcid":"https://orcid.org/0000-0003-2762-0050"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rainer Gemulla","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064647811","display_name":"Spyros Zoupanos","orcid":"https://orcid.org/0000-0002-6069-5241"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Spyros Zoupanos","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088973453"],"corresponding_institution_ids":["https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":16.9882,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.98910626,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"797","last_page":"808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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/T11269","display_name":"Algorithms and Data Compression","score":0.998199999332428,"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/scalability","display_name":"Scalability","score":0.8196333646774292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8097265958786011},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.751649022102356},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.691263735294342},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6406689882278442},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5524649620056152},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5102908611297607},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5007011890411377},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48280155658721924},{"id":"https://openalex.org/keywords/gsp-algorithm","display_name":"GSP Algorithm","score":0.46448928117752075},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.4249381422996521},{"id":"https://openalex.org/keywords/concept-mining","display_name":"Concept mining","score":0.42022407054901123},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37755143642425537},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2623410224914551},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18877926468849182},{"id":"https://openalex.org/keywords/association-rule-learning","display_name":"Association rule learning","score":0.16451618075370789},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.10254514217376709},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09937596321105957},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08636888861656189}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8196333646774292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097265958786011},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.751649022102356},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.691263735294342},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6406689882278442},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5524649620056152},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5102908611297607},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5007011890411377},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48280155658721924},{"id":"https://openalex.org/C87146676","wikidata":"https://www.wikidata.org/wiki/Q5514602","display_name":"GSP Algorithm","level":4,"score":0.46448928117752075},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.4249381422996521},{"id":"https://openalex.org/C176775163","wikidata":"https://www.wikidata.org/wiki/Q5158396","display_name":"Concept mining","level":4,"score":0.42022407054901123},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37755143642425537},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2623410224914551},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18877926468849182},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.16451618075370789},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.10254514217376709},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09937596321105957},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08636888861656189},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C81440476","wikidata":"https://www.wikidata.org/wiki/Q513511","display_name":"Apriori algorithm","level":3,"score":0.0},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2463676.2465285","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2463676.2465285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W191231183","https://openalex.org/W1494776307","https://openalex.org/W1608194207","https://openalex.org/W1631260214","https://openalex.org/W1641039719","https://openalex.org/W1990800901","https://openalex.org/W1999281295","https://openalex.org/W2008475755","https://openalex.org/W2025122101","https://openalex.org/W2032175749","https://openalex.org/W2032226242","https://openalex.org/W2045495924","https://openalex.org/W2056910091","https://openalex.org/W2063771604","https://openalex.org/W2076489648","https://openalex.org/W2109664771","https://openalex.org/W2110893883","https://openalex.org/W2115482638","https://openalex.org/W2120101509","https://openalex.org/W2122182354","https://openalex.org/W2137548844","https://openalex.org/W2155113671","https://openalex.org/W2156026066","https://openalex.org/W2160484851","https://openalex.org/W2166559705","https://openalex.org/W2166951489","https://openalex.org/W2168196587","https://openalex.org/W2168859760","https://openalex.org/W2170036644","https://openalex.org/W2173213060","https://openalex.org/W2621280964","https://openalex.org/W3158986179"],"related_works":["https://openalex.org/W2404647514","https://openalex.org/W1667647204","https://openalex.org/W4247536566","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W4241418540","https://openalex.org/W1508895727","https://openalex.org/W2725786787","https://openalex.org/W2114934675","https://openalex.org/W2903391520"],"abstract_inverted_index":{"Frequent":[0],"sequence":[1,58,106],"mining":[2,43,59,107,131,163],"is":[3,116,167],"one":[4],"of":[5,21,33,80,113,119,122,138,161],"the":[6,14,22,74,88,111,120,159],"fundamental":[7],"building":[8],"blocks":[9],"in":[10,41,91,158],"data":[11],"mining.":[12],"While":[13],"problem":[15],"has":[16],"been":[17],"extensively":[18],"studied,":[19],"few":[20],"available":[23],"techniques":[24,140],"are":[25],"sufficiently":[26],"scalable":[27,54,172],"to":[28,72,76,97],"handle":[29,64],"datasets":[30,37],"with":[31],"billions":[32],"sequences;":[34],"such":[35],"large-scale":[36],"arise,":[38],"for":[39,56],"instance,":[40],"text":[42,162],"and":[44,145,148,171],"session":[45],"analysis.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"propose":[51],"MG-FSM,":[52],"a":[53,77,92,117,123,136],"algorithm":[55],"frequent":[57,81,105,129],"on":[60],"MapReduce.":[61],"MG-FSM":[62,86,166],"can":[63,69],"so-called":[65],"\"gap":[66],"constraints\",":[67],"which":[68,115],"be":[70],"used":[71,126],"limit":[73],"output":[75],"controlled":[78],"set":[79],"sequences.":[82],"At":[83],"its":[84],"heart,":[85],"partitions":[87],"input":[89],"database":[90],"way":[93],"that":[94,141,165],"allows":[95],"us":[96],"mine":[98],"each":[99],"partition":[100,143],"independently":[101],"using":[102],"any":[103],"existing":[104],"algorithm.":[108],"We":[109,133],"introduce":[110],"notion":[112,121],"w-equivalency,":[114],"generalization":[118],"\"projected":[124],"database\"":[125],"by":[127],"many":[128],"pattern":[130],"algorithms.":[132],"also":[134],"present":[135],"number":[137],"optimization":[139],"minimize":[142],"size,":[144],"therefore":[146],"computational":[147],"communication":[149],"costs,":[150],"while":[151],"still":[152],"maintaining":[153],"correctness.":[154],"Our":[155],"experimental":[156],"study":[157],"context":[160],"suggests":[164],"significantly":[168],"more":[169],"efficient":[170],"than":[173],"alternative":[174],"approaches.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}