{"id":"https://openalex.org/W2916595918","doi":"https://doi.org/10.1109/glocom.2018.8647415","title":"Data Deduplication with Edit Errors","display_name":"Data Deduplication with Edit Errors","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2916595918","doi":"https://doi.org/10.1109/glocom.2018.8647415","mag":"2916595918"},"language":"en","primary_location":{"id":"doi:10.1109/glocom.2018.8647415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/glocom.2018.8647415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Global Communications Conference (GLOBECOM)","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/A5081251432","display_name":"Laura Conde-Canencia","orcid":"https://orcid.org/0000-0002-0057-5731"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2802204017","display_name":"Universit\u00e9 de Bretagne Sud","ror":"https://ror.org/04ed7fw48","country_code":"FR","type":"education","lineage":["https://openalex.org/I2802204017"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laura Conde-Canencia","raw_affiliation_strings":["CNRS UMR 6285, Universit\u00e9 Bretagne-Sud, Lorient, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS UMR 6285, Universit\u00e9 Bretagne-Sud, Lorient, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2802204017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014353497","display_name":"Tyson Condie","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tyson Condie","raw_affiliation_strings":["CS Department, University of California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CS Department, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075795132","display_name":"Lara Dolecek","orcid":"https://orcid.org/0000-0003-3736-4345"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lara Dolecek","raw_affiliation_strings":["ECE Department, University of California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ECE Department, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9987000226974487,"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/T11478","display_name":"Caching and Content Delivery","score":0.9968000054359436,"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":0.9807648658752441},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7821893692016602},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6443005204200745},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.48236483335494995},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4695967435836792},{"id":"https://openalex.org/keywords/brute-force","display_name":"Brute force","score":0.41150274872779846},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2872017025947571},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1581813395023346},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06311303377151489}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9807648658752441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821893692016602},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6443005204200745},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.48236483335494995},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4695967435836792},{"id":"https://openalex.org/C2986801135","wikidata":"https://www.wikidata.org/wiki/Q1209494","display_name":"Brute force","level":2,"score":0.41150274872779846},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2872017025947571},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1581813395023346},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06311303377151489},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/glocom.2018.8647415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/glocom.2018.8647415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Global Communications Conference (GLOBECOM)","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":8,"referenced_works":["https://openalex.org/W1474119323","https://openalex.org/W2101398931","https://openalex.org/W2107745473","https://openalex.org/W2156719566","https://openalex.org/W2161628678","https://openalex.org/W2308303010","https://openalex.org/W2317556569","https://openalex.org/W2963294730"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W4385804830","https://openalex.org/W2943088381","https://openalex.org/W2144348063","https://openalex.org/W2074021203","https://openalex.org/W3157678865","https://openalex.org/W2610921154"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"tackle":[4],"the":[5,16,19,33,46,61,64,81,97,100,111],"problem":[6],"of":[7,48,63,83,99,113],"file":[8,57],"deduplication":[9,20,41,54,58,89,115],"for":[10],"efficient":[11],"data":[12],"storage.":[13],"We":[14,36,91],"consider":[15],"case":[17,47],"where":[18,56],"is":[21],"performed":[22],"on":[23,60,96],"files":[24,74],"that":[25,72],"are":[26],"modified":[27],"by":[28],"edit":[29],"errors":[30],"relative":[31],"to":[32,52,68,103,109],"original":[34],"version.":[35],"propose":[37],"a":[38,93],"novel":[39],"block-level":[40],"algorithm":[42,78,101],"with":[43],"variable-lengths":[44],"in":[45],"non-binary":[49],"alphabets.":[50],"Compared":[51],"hash-based":[53],"algorithms":[55],"depends":[59],"content":[62],"hash":[65],"keys":[66],"or":[67],"brute":[69],"force":[70],"methods":[71,105],"compare":[73],"symbol-by-":[75],"symbol,":[76],"our":[77,114],"significantly":[79],"reduces":[80],"number":[82],"symbol":[84],"comparisons":[85],"and":[86,106],"achieves":[87],"high":[88],"ratios.":[90],"present":[92],"theoretical":[94],"analysis":[95],"cost":[98],"compared":[102],"naive":[104],"experimental":[107],"results":[108],"evaluate":[110],"efficiency":[112],"algorithm.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
