{"id":"https://openalex.org/W2946064759","doi":"https://doi.org/10.1109/tkde.2019.2916858","title":"Similarity Search for Dynamic Data Streams","display_name":"Similarity Search for Dynamic Data Streams","publication_year":2019,"publication_date":"2019-05-14","ids":{"openalex":"https://openalex.org/W2946064759","doi":"https://doi.org/10.1109/tkde.2019.2916858","mag":"2946064759"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2019.2916858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2019.2916858","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11573/1399064","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016911982","display_name":"Marc Bury","orcid":null},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Marc Bury","raw_affiliation_strings":["TU Dortmund, Dortmund, Germany"],"affiliations":[{"raw_affiliation_string":"TU Dortmund, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080748807","display_name":"Chris Schwiegelshohn","orcid":"https://orcid.org/0000-0002-1202-0805"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Chris Schwiegelshohn","raw_affiliation_strings":["Sapienza University of Rome, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032279305","display_name":"Mara Sorella","orcid":"https://orcid.org/0000-0003-0622-2109"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mara Sorella","raw_affiliation_strings":["Sapienza University of Rome, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016911982"],"corresponding_institution_ids":["https://openalex.org/I200332995"],"apc_list":null,"apc_paid":null,"fwci":0.7074,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.72568753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"32","issue":"11","first_page":"2241","last_page":"2253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9997000098228455,"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/T11478","display_name":"Caching and Content Delivery","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9926999807357788,"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/computer-science","display_name":"Computer science","score":0.8582919239997864},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.848423957824707},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.658336877822876},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6480514407157898},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.6353108286857605},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6173402667045593},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5928974747657776},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.5140889286994934},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44040510058403015},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.4142998158931732},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.3867512345314026},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3669654130935669},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.33791667222976685},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.24853456020355225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1968984305858612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582919239997864},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.848423957824707},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.658336877822876},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6480514407157898},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.6353108286857605},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6173402667045593},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5928974747657776},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.5140889286994934},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44040510058403015},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.4142998158931732},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.3867512345314026},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3669654130935669},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.33791667222976685},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.24853456020355225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1968984305858612},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2019.2916858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2019.2916858","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1399064","is_oa":true,"landing_page_url":"http://hdl.handle.net/11573/1399064","pdf_url":"http://hdl.handle.net/11573/1399064","source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:iris.uniroma1.it:11573/1399064","is_oa":true,"landing_page_url":"http://hdl.handle.net/11573/1399064","pdf_url":"http://hdl.handle.net/11573/1399064","source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2946064759.pdf","grobid_xml":"https://content.openalex.org/works/W2946064759.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1546441687","https://openalex.org/W1968161494","https://openalex.org/W1979819093","https://openalex.org/W1993091968","https://openalex.org/W1995945562","https://openalex.org/W2003184432","https://openalex.org/W2008886893","https://openalex.org/W2010833880","https://openalex.org/W2011737794","https://openalex.org/W2012833704","https://openalex.org/W2038276547","https://openalex.org/W2048779798","https://openalex.org/W2057712948","https://openalex.org/W2060536778","https://openalex.org/W2070996757","https://openalex.org/W2081193615","https://openalex.org/W2097332592","https://openalex.org/W2097865464","https://openalex.org/W2103126020","https://openalex.org/W2106446203","https://openalex.org/W2120031510","https://openalex.org/W2123427850","https://openalex.org/W2131850886","https://openalex.org/W2132069633","https://openalex.org/W2134212491","https://openalex.org/W2143326696","https://openalex.org/W2147017814","https://openalex.org/W2147717514","https://openalex.org/W2148885851","https://openalex.org/W2152565070","https://openalex.org/W2188225224","https://openalex.org/W2221439497","https://openalex.org/W2241750177","https://openalex.org/W2245405994","https://openalex.org/W2245536463","https://openalex.org/W2296677182","https://openalex.org/W2407340388","https://openalex.org/W2408675303","https://openalex.org/W2479183965","https://openalex.org/W2521278809","https://openalex.org/W2563258058","https://openalex.org/W2752494670","https://openalex.org/W2783123230","https://openalex.org/W2949921088","https://openalex.org/W2962733107","https://openalex.org/W2962766560","https://openalex.org/W4230940751","https://openalex.org/W4246180860","https://openalex.org/W4285719527","https://openalex.org/W4300601563","https://openalex.org/W6678016754","https://openalex.org/W6679663036","https://openalex.org/W6682042839","https://openalex.org/W6731251488","https://openalex.org/W6743868871"],"related_works":["https://openalex.org/W2911483473","https://openalex.org/W2885569103","https://openalex.org/W3094967175","https://openalex.org/W2166822184","https://openalex.org/W2135779989","https://openalex.org/W3083090961","https://openalex.org/W2045263322","https://openalex.org/W2393322642","https://openalex.org/W2754607325","https://openalex.org/W2901290148"],"abstract_inverted_index":{"Nearest":[0],"neighbor":[1,90],"searching":[2],"systems":[3],"are":[4,45,145],"an":[5,32,57],"integral":[6],"part":[7],"of":[8,36,68,101,168,212,232],"many":[9,120],"online":[10],"applications,":[11],"including":[12],"but":[13,109],"not":[14],"limited":[15],"to":[16,66,75,86,148,151,156,216],"pattern":[17],"recognition,":[18],"plagiarism":[19],"detection,":[20],"and":[21,40,71,115,133,142,154,197,225],"recommender":[22],"systems.":[23],"With":[24],"increasingly":[25],"larger":[26],"data":[27,54,95,128,195],"sets,":[28],"scalability":[29],"has":[30],"become":[31],"important":[33],"issue.":[34],"Many":[35],"the":[37,53,72,166,179,221],"most":[38],"space":[39,113],"running":[41,213],"time":[42,214],"efficient":[43,114],"algorithms":[44,206,229],"based":[46],"on":[47,92],"locality-sensitive":[48,170],"hashing.":[49],"Here,":[50],"we":[51,185],"view":[52],"set":[55,96],"as":[56,131,182],"n":[58,69],"by":[59],"lUl":[60],"matrix":[61],"where":[62],"each":[63],"row":[64],"corresponds":[65],"one":[67],"users":[70],"columns":[73],"correspond":[74],"items":[76,160],"drawn":[77],"from":[78],"a":[79,94,99,136,188,199],"universe":[80],"U.":[81],"The":[82],"de-facto":[83],"standard":[84],"approach":[85],"quickly":[87],"answer":[88],"nearest":[89],"queries":[91],"such":[93,130],"is":[97,105,111,139],"usually":[98],"form":[100],"min-hashing.":[102],"Not":[103],"only":[104,146,223],"min-hashing":[106],"very":[107],"fast,":[108],"it":[110],"also":[112],"can":[116],"be":[117,162],"implemented":[118],"in":[119,193,210,230],"computational":[121],"models":[122],"aimed":[123],"at":[124],"dealing":[125],"with":[126],"large":[127],"sets":[129],"MapReduce":[132],"streaming.":[134],"However,":[135],"significant":[137],"drawback":[138],"that":[140],"minhashing":[141],"related":[143],"methods":[144],"able":[147],"handle":[149],"insertions":[150],"user":[152],"profiles":[153],"tend":[155],"perform":[157],"poorly":[158],"when":[159],"may":[161],"removed.":[163],"We":[164],"initiate":[165],"study":[167],"scalable":[169],"hashing":[171],"(LSH)":[172],"for":[173,202,220],"fully":[174],"dynamic":[175,194],"data-streams.":[176],"Specifically,":[177],"using":[178],"Jaccard":[180],"index":[181],"similarity":[183,203],"measure,":[184],"design":[186],"(1)":[187],"collaborative":[189],"filtering":[190],"mechanism":[191],"maintainable":[192],"streams":[196],"(2)":[198],"sketching":[200],"algorithm":[201],"estimation.":[204],"Our":[205],"have":[207],"little":[208],"overhead":[209],"terms":[211],"compared":[215],"previous":[217,228],"LSH":[218],"approaches":[219],"insertion":[222],"case,":[224],"drastically":[226],"outperform":[227],"case":[231],"deletions.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}