{"id":"https://openalex.org/W2281363974","doi":null,"title":"SiLo: a similarity-locality based near-exact deduplication scheme with low RAM overhead and high throughput","display_name":"SiLo: a similarity-locality based near-exact deduplication scheme with low RAM overhead and high throughput","publication_year":2011,"publication_date":"2011-06-15","ids":{"openalex":"https://openalex.org/W2281363974","mag":"2281363974"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.307.1179","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.307.1179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.usenix.org/legacy/events/atc11/tech/final_files/Xia.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5050928208","display_name":"Wen Xia","orcid":"https://orcid.org/0000-0003-4093-6391","observed_orcids":["https://orcid.org/0000-0003-4093-6391"]},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Xia","raw_affiliation_strings":["School of Computer, Huazhong University of Science and Technology, Wuhan, China and Wuhan National Lab for Optoelectronics, Wuhan, China#TAB#"],"raw_orcid":"https://orcid.org/0000-0003-4093-6391","affiliations":[{"raw_affiliation_string":"School of Computer, Huazhong University of Science and Technology, Wuhan, China and Wuhan National Lab for Optoelectronics, Wuhan, China#TAB#","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054285749","display_name":"Hong Jiang","orcid":"https://orcid.org/0000-0002-1477-9751","observed_orcids":["https://orcid.org/0000-0002-1477-9751"]},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Jiang","raw_affiliation_strings":["Dept. of Comput. Sci. & Eng., Univ. of Nebraska - Lincoln, Lincoln, NE"],"raw_orcid":"https://orcid.org/0000-0002-1477-9751","affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Univ. of Nebraska - Lincoln, Lincoln, NE","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057421680","display_name":"Dan Feng","orcid":"https://orcid.org/0000-0002-4674-6006","observed_orcids":["https://orcid.org/0000-0002-4674-6006"]},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Feng","raw_affiliation_strings":["School of Computer, Huazhong University of Science and Technology, Wuhan, China and Wuhan National Lab for Optoelectronics, Wuhan, China#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-4674-6006","affiliations":[{"raw_affiliation_string":"School of Computer, Huazhong University of Science and Technology, Wuhan, China and Wuhan National Lab for Optoelectronics, Wuhan, China#TAB#","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088998781","display_name":"Yu Hua","orcid":"https://orcid.org/0000-0001-7730-3796","observed_orcids":["https://orcid.org/0000-0001-7730-3796"]},"institutions":[{"id":"https://openalex.org/I4210138186","display_name":"Wuhan National Laboratory for Optoelectronics","ror":"https://ror.org/03c9ncn37","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210138186"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Hua","raw_affiliation_strings":["School of Computer, Huazhong University of Science and Technology, Wuhan, China and Wuhan National Lab for Optoelectronics, Wuhan, China and Dept. of Computer Science and Engineering, University o ...#TAB#"],"raw_orcid":"https://orcid.org/0000-0001-7730-3796","affiliations":[{"raw_affiliation_string":"School of Computer, Huazhong University of Science and Technology, Wuhan, China and Wuhan National Lab for Optoelectronics, Wuhan, China and Dept. of Computer Science and Engineering, University o ...#TAB#","institution_ids":["https://openalex.org/I4210138186","https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.8304,"has_fulltext":false,"cited_by_count":189,"citation_normalized_percentile":{"value":0.99482823,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980000257492065,"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":0.9980000257492065,"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/T11719","display_name":"Data Quality and Management","score":0.000699999975040555,"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/T11269","display_name":"Algorithms and Data Compression","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-deduplication","display_name":"data deduplication","score":0.9769999980926514},{"id":"https://openalex.org/keywords/storage-systems","display_name":"storage systems","score":0.6430000066757202},{"id":"https://openalex.org/keywords/file-segmentation","display_name":"file segmentation","score":0.6690000295639038}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9246245622634888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7958650588989258},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7622439861297607},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.665199875831604},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.5624560117721558},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5391898155212402},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4866815209388733},{"id":"https://openalex.org/C2778024958","wikidata":"https://www.wikidata.org/wiki/Q213643","display_name":"Silo","level":2,"score":0.4716429114341736},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4385015368461609},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3949817419052124},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33862242102622986},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09654119610786438},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08379966020584106},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.307.1179","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.307.1179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.usenix.org/legacy/events/atc11/tech/final_files/Xia.pdf","raw_type":"text"},{"id":"mag:2281363974","doi":null,"is_oa":false,"landing_page_url":"https://static.usenix.org/event/atc11/tech/final_files/Xia.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306421113","display_name":"USENIX Annual Technical Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"USENIX Annual Technical Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W69510097","https://openalex.org/W126194223","https://openalex.org/W174289249","https://openalex.org/W200233886","https://openalex.org/W1490390347","https://openalex.org/W1521407587","https://openalex.org/W1541467180","https://openalex.org/W1576397915","https://openalex.org/W1609518033","https://openalex.org/W1929726975","https://openalex.org/W1963535513","https://openalex.org/W1969067141","https://openalex.org/W1969126835","https://openalex.org/W1971212200","https://openalex.org/W1998817683","https://openalex.org/W2056980397","https://openalex.org/W2083695892","https://openalex.org/W2112671267","https://openalex.org/W2114553826","https://openalex.org/W2123767107","https://openalex.org/W2132069633","https://openalex.org/W2147407897","https://openalex.org/W2160127232"],"related_works":["https://openalex.org/W2124632914","https://openalex.org/W380853792","https://openalex.org/W2179326652","https://openalex.org/W200233886","https://openalex.org/W69510097","https://openalex.org/W3147631500","https://openalex.org/W2378402762","https://openalex.org/W2188247367","https://openalex.org/W7097125055","https://openalex.org/W2990640343"],"abstract_inverted_index":{"Data":[0],"Deduplication":[1],"is":[2,51,74,116,177],"becoming":[3],"increasingly":[4],"popular":[5],"in":[6,39,56,140],"storage":[7],"systems":[8],"as":[9],"a":[10,75,87,130,188],"space-efficient":[11],"approach":[12,176],"to":[13,32,62,99,117,137,150,179],"data":[14,71,155],"backup":[15,142],"and":[16,64,93,97,104,119,132,136,153,171,186,208,219],"archiving.":[17],"Most":[18],"existing":[19,212],"state-of-the-art":[20],"deduplication":[21,47,89,191],"methods":[22],"are":[23],"either":[24],"locality":[25,55,98,139,170],"based":[26,198,216,222],"or":[27,53],"similarity":[28,78,96,122,160,165,218],"based,":[29],"which,":[30],"according":[31],"our":[33],"analysis,":[34],"do":[35],"not":[36],"work":[37],"adequately":[38],"many":[40],"situations.":[41],"While":[42],"the":[43,58,141,158,167,174,204,220],"former":[44],"produces":[45],"poor":[46],"throughput":[48,105],"when":[49,72],"there":[50,73],"little":[52],"no":[54],"datasets,":[57],"latter":[59],"can":[60],"fail":[61],"identify":[63],"thus":[65],"remove":[66],"significant":[67],"amounts":[68],"of":[69,77,169,196],"redundant":[70],"lack":[76],"among":[79],"files.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84],"present":[85],"SiLo,":[86],"near-exact":[88],"system":[90,206],"that":[91,203],"effectively":[92],"complementarily":[94],"exploits":[95],"achieve":[100],"high":[101,190],"duplicate":[102,154],"elimination":[103],"at":[106],"extremely":[107],"low":[108],"RAM":[109,182],"overheads.":[110],"The":[111],"main":[112],"idea":[113],"behind":[114],"SiLo":[115,175,197,205],"expose":[118],"exploit":[120],"more":[121],"by":[123,144,157],"grouping":[124,145],"strongly":[125],"correlated":[126],"small":[127],"files":[128],"into":[129,148],"segment":[131],"segmenting":[133],"large":[134],"files,":[135],"leverage":[138],"stream":[143],"contiguous":[146],"segments":[147],"blocks":[149],"capture":[151],"similar":[152],"missed":[156],"probabilistic":[159],"detection.":[161],"By":[162],"judiciously":[163],"enhancing":[164],"through":[166],"exploitation":[168],"vice":[172],"versa,":[173],"able":[178],"significantly":[180,209],"reduce":[181],"usage":[183],"for":[184],"indexlookup":[185],"maintain":[187],"very":[189],"throughput.":[192],"Our":[193],"experimental":[194],"evaluation":[195],"on":[199,217,223],"realworld":[200],"datasets":[201],"shows":[202],"consistently":[207],"outperforms":[210],"two":[211],"state-of-theart":[213],"system,":[214],"one":[215],"other":[221],"locality,":[224],"under":[225],"various":[226],"workload":[227],"conditions.":[228],"1":[229]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":28},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":22},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":15}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}
