{"id":"https://openalex.org/W1993736757","doi":"https://doi.org/10.1145/1458082.1458226","title":"Data weaving","display_name":"Data weaving","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W1993736757","doi":"https://doi.org/10.1145/1458082.1458226","mag":"1993736757"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458226","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM 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/A5005515091","display_name":"Ron Bekkerman","orcid":"https://orcid.org/0000-0001-5636-694X"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ron Bekkerman","raw_affiliation_strings":["HP Laboratories, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Laboratories, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025801122","display_name":"Martin Scholz","orcid":"https://orcid.org/0009-0005-4421-9412"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Scholz","raw_affiliation_strings":["HP Laboratories, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"HP Laboratories, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005515091"],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":2.1205,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.87408198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1083","last_page":"1092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9929999709129333,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9894000291824341,"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/weaving","display_name":"Weaving","score":0.8652652502059937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5521732568740845},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15491798520088196},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.08366745710372925}],"concepts":[{"id":"https://openalex.org/C54525549","wikidata":"https://www.wikidata.org/wiki/Q2553445","display_name":"Weaving","level":2,"score":0.8652652502059937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5521732568740845},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15491798520088196},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.08366745710372925}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1458082.1458226","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W26772505","https://openalex.org/W37503237","https://openalex.org/W245990283","https://openalex.org/W1498355188","https://openalex.org/W1547561528","https://openalex.org/W1547566968","https://openalex.org/W1554544485","https://openalex.org/W1587018874","https://openalex.org/W1676212923","https://openalex.org/W1686946872","https://openalex.org/W1857926807","https://openalex.org/W1870625491","https://openalex.org/W1880262756","https://openalex.org/W1963820332","https://openalex.org/W1964937891","https://openalex.org/W1981472895","https://openalex.org/W1988157641","https://openalex.org/W2010425028","https://openalex.org/W2016464611","https://openalex.org/W2026386905","https://openalex.org/W2036216970","https://openalex.org/W2039765803","https://openalex.org/W2060683726","https://openalex.org/W2103723258","https://openalex.org/W2107728069","https://openalex.org/W2109722477","https://openalex.org/W2112617148","https://openalex.org/W2117848638","https://openalex.org/W2127137551","https://openalex.org/W2138745909","https://openalex.org/W2150102617","https://openalex.org/W2158148763","https://openalex.org/W2173213060","https://openalex.org/W2434205482","https://openalex.org/W2610184409","https://openalex.org/W2613433911","https://openalex.org/W2785356762","https://openalex.org/W2903691225","https://openalex.org/W2978329087","https://openalex.org/W4285719527","https://openalex.org/W4388323202","https://openalex.org/W6632663641","https://openalex.org/W6633362792","https://openalex.org/W6637108112","https://openalex.org/W6639073361","https://openalex.org/W6660493486","https://openalex.org/W6675471587","https://openalex.org/W6676367512","https://openalex.org/W6747634744"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2952092742","https://openalex.org/W2068981955","https://openalex.org/W67774003","https://openalex.org/W2368396969","https://openalex.org/W4231951841","https://openalex.org/W2027559301","https://openalex.org/W2740565117","https://openalex.org/W2188987414","https://openalex.org/W2365680989"],"abstract_inverted_index":{"The":[0],"enormous":[1],"amount":[2],"and":[3,58,174],"dimensionality":[4],"of":[5,22,78,113,117,176],"data":[6,10,92,118,123],"processed":[7],"by":[8,75],"modern":[9],"mining":[11],"tools":[12],"require":[13],"effective,":[14],"scalable":[15],"unsupervised":[16],"learning":[17],"techniques.":[18],"Unfortunately,":[19],"the":[20,45,76,168],"majority":[21],"previously":[23],"proposed":[24],"clustering":[25,38,48,101,112,164],"algorithms":[26],"are":[27,55,72],"either":[28],"effective":[29],"or":[30],"scalable.":[31,61],"This":[32],"paper":[33],"is":[34,105],"concerned":[35],"with":[36,140,180],"information-theoretic":[37],"(ITC)":[39],"that":[40,66],"has":[41],"historically":[42],"been":[43],"considered":[44],"state-of-the-art":[46],"in":[47,131],"multi-dimensional":[49],"data.":[50],"Most":[51],"existing":[52],"ITC":[53,64],"methods":[54,65],"computationally":[56],"expensive":[57,150],"not":[59],"easily":[60],"Those":[62],"few":[63,115],"scale":[67],"well":[68],"(using,":[69],"e.g.,":[70],"parallelization)":[71],"often":[73],"outperformed":[74],"others,":[77],"an":[79],"inherently":[80],"sequential":[81,100,151],"nature.":[82],"First,":[83],"we":[84,121,170],"justify":[85],"this":[86],"observation":[87],"theoretically.":[88],"We":[89],"then":[90],"propose":[91],"weaving":[93,104,124],"-":[94,108],"a":[95,114,133,177],"novel":[96],"method":[97],"for":[98],"parallelizing":[99],"algorithms.":[102],"Data":[103],"intrinsically":[106],"multi-modal":[107,127],"it":[109],"allows":[110],"simultaneous":[111],"types":[116],"(modalities).":[119],"Finally,":[120],"use":[122],"to":[125,149],"parallelize":[126],"ITC,":[128],"which":[129],"results":[130],"proposing":[132],"powerful":[134],"DataLoom":[135,143,157],"algorithm.":[136],"In":[137],"our":[138],"experimentation":[139],"small":[141],"datasets,":[142,155],"shows":[144],"practically":[145],"identical":[146],"performance":[147],"compared":[148],"alternatives.":[152],"On":[153],"large":[154],"however,":[156],"demonstrates":[158],"significant":[159],"gains":[160],"over":[161,181],"other":[162],"parallel":[163],"methods.":[165],"To":[166],"illustrate":[167],"scalability,":[169],"simultaneously":[171],"clustered":[172],"rows":[173],"columns":[175],"contingency":[178],"table":[179],"120":[182],"billion":[183],"entries.":[184]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}