{"id":"https://openalex.org/W2074021203","doi":"https://doi.org/10.1109/pccc.2012.6407746","title":"Improved deduplication through parallel Binning","display_name":"Improved deduplication through parallel Binning","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2074021203","doi":"https://doi.org/10.1109/pccc.2012.6407746","mag":"2074021203"},"language":"en","primary_location":{"id":"doi:10.1109/pccc.2012.6407746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pccc.2012.6407746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 31st International Performance Computing and Communications Conference (IPCCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5108384834","display_name":"Zhike Zhang","orcid":"https://orcid.org/0000-0002-8726-3174"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhike Zhang","raw_affiliation_strings":["Univ. of California, Santa Cruz, CA","University of California, Santa Cruz, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of California, Santa Cruz, CA","institution_ids":["https://openalex.org/I185103710"]},{"raw_affiliation_string":"University of California, Santa Cruz, CA#TAB#","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058889435","display_name":"Deepavali Bhagwat","orcid":null},"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":"Deepavali Bhagwat","raw_affiliation_strings":["Hewlett Packard Company, Palo Alto, CA","Hewlett-Packard Company (Palo  Alto, CA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett Packard Company, Palo Alto, CA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard Company (Palo  Alto, CA)","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063763327","display_name":"Witold Litwin","orcid":"https://orcid.org/0009-0009-2999-9704"},"institutions":[{"id":"https://openalex.org/I56435720","display_name":"Universit\u00e9 Paris Dauphine-PSL","ror":"https://ror.org/052bz7812","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580","https://openalex.org/I56435720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Witold Litwin","raw_affiliation_strings":["Universit\u00e9 Paris Dauphine, Paris, France","Universite Paris Dauphine, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Dauphine, Paris, France","institution_ids":["https://openalex.org/I56435720"]},{"raw_affiliation_string":"Universite Paris Dauphine, Paris, France","institution_ids":["https://openalex.org/I56435720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029994088","display_name":"Darrell D. E. Long","orcid":"https://orcid.org/0000-0002-0822-0740"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Darrell Long","raw_affiliation_strings":["Univ. of California, Santa Cruz, CA","University of California, Santa Cruz, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of California, Santa Cruz, CA","institution_ids":["https://openalex.org/I185103710"]},{"raw_affiliation_string":"University of California, Santa Cruz, CA#TAB#","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048161711","display_name":"Thomas Schwarz","orcid":"https://orcid.org/0000-0003-4433-3360"},"institutions":[{"id":"https://openalex.org/I875251973","display_name":"Universidad Cat\u00f3lica del Uruguay","ror":"https://ror.org/019xvpc30","country_code":"UY","type":"education","lineage":["https://openalex.org/I875251973"]}],"countries":["UY"],"is_corresponding":false,"raw_author_name":"S. J. Thomas Schwarz","raw_affiliation_strings":["Univ. Cat\u00f3lica del Uruguay, Montevideo, Uruguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Cat\u00f3lica del Uruguay, Montevideo, Uruguay","institution_ids":["https://openalex.org/I875251973"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"130","last_page":"141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11478","display_name":"Caching and Content Delivery","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.9941504001617432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8337323665618896},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7384012937545776},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.41109031438827515},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38710981607437134},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.335703581571579}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9941504001617432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8337323665618896},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7384012937545776},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.41109031438827515},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38710981607437134},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.335703581571579},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/pccc.2012.6407746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pccc.2012.6407746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 31st International Performance Computing and Communications Conference (IPCCC)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.379.8974","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.379.8974","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ssrc.ucsc.edu/Papers/zhang-ipccc12.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01495371v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01495371","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2012 IEEE 31st International Performance Computing and Communications Conference (IPCCC), Dec 2012, Austin, United States. pp.130-141, &#x27E8;10.1109/PCCC.2012.6407746&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:basepub.dauphine.fr:123456789/11821","is_oa":false,"landing_page_url":"https://basepub.dauphine.fr/handle/123456789/11821","pdf_url":null,"source":{"id":"https://openalex.org/S4306401007","display_name":"Base Institutionnelle de Recherche de l'universit\u00e9 Paris-Dauphine (BIRD) (University Paris-Dauphine)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102197404","host_organization_name":"Universit\u00e9 Paris-Sud","host_organization_lineage":["https://openalex.org/I102197404"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Communication / Conf\u00e9rence"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309475","display_name":"Northwestern University","ror":"https://ror.org/000e0be47"},{"id":"https://openalex.org/F4320321392","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W69510097","https://openalex.org/W200233886","https://openalex.org/W1508926177","https://openalex.org/W1576397915","https://openalex.org/W1963535513","https://openalex.org/W1969126835","https://openalex.org/W1998817683","https://openalex.org/W2005611725","https://openalex.org/W2038908732","https://openalex.org/W2056980397","https://openalex.org/W2107551255","https://openalex.org/W2123767107","https://openalex.org/W2132069633","https://openalex.org/W2148885851","https://openalex.org/W2472668849","https://openalex.org/W6602837329","https://openalex.org/W6608138927","https://openalex.org/W6630499100","https://openalex.org/W6634463810","https://openalex.org/W6679663036","https://openalex.org/W6682205557"],"related_works":["https://openalex.org/W1437397736","https://openalex.org/W4285245558","https://openalex.org/W2048606985","https://openalex.org/W2375056709","https://openalex.org/W2012359782","https://openalex.org/W2952411620","https://openalex.org/W4301155776","https://openalex.org/W2348132657","https://openalex.org/W1481447012","https://openalex.org/W4236228546"],"abstract_inverted_index":{"Many":[0],"modern":[1],"storage":[2],"systems":[3],"use":[4,21],"deduplication":[5,41,66],"in":[6,24],"order":[7],"to":[8,20,51,58],"compress":[9],"data":[10,16,22,32,47],"by":[11],"avoiding":[12],"storing":[13],"the":[14,25,77,80],"same":[15],"twice.":[17],"Deduplication":[18],"needs":[19],"stored":[23,33],"past,":[26],"but":[27],"accessing":[28],"information":[29,44],"about":[30],"all":[31],"can":[34],"cause":[35],"a":[36],"severe":[37],"bottleneck.":[38],"Similarity":[39],"based":[40],"only":[42],"accesses":[43],"on":[45],"past":[46],"that":[48,68],"is":[49],"likely":[50,57],"be":[52],"similar":[53],"and":[54,72,75],"thus":[55],"more":[56],"yield":[59],"good":[60],"deduplication.":[61],"We":[62],"present":[63],"an":[64],"adaptive":[65],"strategy":[67],"extends":[69],"Extreme":[70],"Binning":[71],"investigate":[73],"theoretically":[74],"experimentally":[76],"effects":[78],"of":[79],"additional":[81],"bin":[82],"accesses.":[83]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
