{"id":"https://openalex.org/W2909864759","doi":"https://doi.org/10.1109/globecom38437.2019.9014012","title":"Generalized Deduplication: Bounds, Convergence, and Asymptotic Properties","display_name":"Generalized Deduplication: Bounds, Convergence, and Asymptotic Properties","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2909864759","doi":"https://doi.org/10.1109/globecom38437.2019.9014012","mag":"2909864759"},"language":"en","primary_location":{"id":"doi:10.1109/globecom38437.2019.9014012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom38437.2019.9014012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Global Communications Conference (GLOBECOM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1901.02720","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019917624","display_name":"Rasmus Vestergaard","orcid":"https://orcid.org/0000-0002-0815-0148"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Rasmus Vestergaard","raw_affiliation_strings":["DIGIT and Department of Engineering, Aarhus University, Denmark"],"affiliations":[{"raw_affiliation_string":"DIGIT and Department of Engineering, Aarhus University, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360194","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0001-5303-9804"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["DIGIT and Department of Engineering, Aarhus University, Denmark"],"affiliations":[{"raw_affiliation_string":"DIGIT and Department of Engineering, Aarhus University, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110828662","display_name":"Daniel E. Lucani","orcid":null},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Daniel E. Lucani","raw_affiliation_strings":["DIGIT and Department of Engineering, Aarhus University, Denmark"],"affiliations":[{"raw_affiliation_string":"DIGIT and Department of Engineering, Aarhus University, Denmark","institution_ids":["https://openalex.org/I204337017"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019917624"],"corresponding_institution_ids":["https://openalex.org/I204337017"],"apc_list":null,"apc_paid":null,"fwci":3.613,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.94318384,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9995999932289124,"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/T11017","display_name":"Chaos-based Image/Signal Encryption","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.980107307434082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7058729529380798},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.5689330101013184},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4973805248737335},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49563825130462646},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.49172523617744446},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44129887223243713},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4256870746612549},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.38735467195510864},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3419470191001892},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27976489067077637},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12910419702529907}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.980107307434082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7058729529380798},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.5689330101013184},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4973805248737335},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49563825130462646},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.49172523617744446},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44129887223243713},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4256870746612549},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.38735467195510864},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3419470191001892},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27976489067077637},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12910419702529907},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/globecom38437.2019.9014012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom38437.2019.9014012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Global Communications Conference (GLOBECOM)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1901.02720","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.02720","pdf_url":"https://arxiv.org/pdf/1901.02720","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:publications/ab66e6e7-8661-4c86-bdae-d2405c77ac49","is_oa":false,"landing_page_url":"https://pure.au.dk/portal/en/publications/ab66e6e7-8661-4c86-bdae-d2405c77ac49","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Vestergaard, R, Zhang, Q & Lucani R\u00f6tter, D E 2019, Generalized Deduplication: Bounds, Convergence, and Asymptotic Properties. in 2019 IEEE Global Communications Conference, GLOBECOM 2019 - Proceedings., 9014012, IEEE, IEEE Global Communications (GLOBECOM 2019), Kona, United States, 08/12/2019. https://doi.org/10.1109/GLOBECOM38437.2019.9014012","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1901.02720","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.02720","pdf_url":"https://arxiv.org/pdf/1901.02720","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W280536263","https://openalex.org/W1474119323","https://openalex.org/W1580101844","https://openalex.org/W1600963723","https://openalex.org/W2060108852","https://openalex.org/W2096798913","https://openalex.org/W2106981684","https://openalex.org/W2107745473","https://openalex.org/W2110322986","https://openalex.org/W2122962290","https://openalex.org/W2475932436","https://openalex.org/W2909864759","https://openalex.org/W2963294730","https://openalex.org/W3010302802","https://openalex.org/W3044766408","https://openalex.org/W3102843100","https://openalex.org/W4213059792","https://openalex.org/W6675802084","https://openalex.org/W6780883385"],"related_works":["https://openalex.org/W2948148442","https://openalex.org/W2461250372","https://openalex.org/W2394342941","https://openalex.org/W2169853506","https://openalex.org/W2547124190","https://openalex.org/W2350586049","https://openalex.org/W2385628723","https://openalex.org/W2032414556","https://openalex.org/W2169871401","https://openalex.org/W2057878850"],"abstract_inverted_index":{"We":[0,27],"study":[1],"a":[2,24,123],"generalization":[3,112],"of":[4,10,34,65,109,126,139],"deduplication,":[5,85,128],"which":[6,86],"enables":[7],"lossless":[8],"deduplication":[9,18,39,60,76],"highly":[11],"similar":[12],"data":[13,141],"and":[14,40,104],"show":[15,41,57,119],"that":[16,42,58,74,98,120],"classic":[17,70,84,114],"with":[19,136],"fixed":[20],"chunk":[21],"length":[22,33],"is":[23,87,134],"special":[25],"case.":[26],"provide":[28,78],"bounds":[29,101],"on":[30],"the":[31,43,50,106,111,129,137,140],"expected":[32],"coded":[35],"sequences":[36],"for":[37,62,122],"generalized":[38,59,75,127],"coding":[44],"has":[45],"asymptotic":[46],"near-entropy":[47],"cost":[48],"under":[49],"proposed":[51],"source":[52],"model.":[53],"More":[54],"importantly,":[55],"we":[56,118],"allows":[61],"multiple":[63],"orders":[64],"magnitude":[66],"faster":[67],"convergence":[68,132],"than":[69,83],"deduplication.":[71,115],"This":[72],"means":[73],"can":[77],"compression":[79],"benefits":[80],"much":[81],"earlier":[82],"key":[88],"in":[89,131],"practical":[90],"systems.":[91],"Numerical":[92],"examples":[93],"demonstrate":[94],"our":[95,99],"results,":[96],"showing":[97],"lower":[100],"are":[102],"achievable,":[103],"illustrating":[105],"potential":[107],"gain":[108,130],"using":[110],"over":[113],"In":[116],"fact,":[117],"even":[121],"simple":[124],"case":[125],"speed":[133],"linear":[135],"size":[138],"chunks.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}