{"id":"https://openalex.org/W3211968096","doi":"https://doi.org/10.1109/tkde.2021.3126631","title":"Dynamic Set Similarity Join: An Update Log Based Approach","display_name":"Dynamic Set Similarity Join: An Update Log Based Approach","publication_year":2021,"publication_date":"2021-11-09","ids":{"openalex":"https://openalex.org/W3211968096","doi":"https://doi.org/10.1109/tkde.2021.3126631","mag":"3211968096"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2021.3126631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3126631","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077342332","display_name":"Chengcheng Yang","orcid":"https://orcid.org/0000-0001-5128-8882"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengcheng Yang","raw_affiliation_strings":["Shanghai Engineering Research Center of Big Data Management, School of Data Science and Engineering, East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Engineering Research Center of Big Data Management, School of Data Science and Engineering, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002042909","display_name":"Lisi Chen","orcid":"https://orcid.org/0000-0003-4233-3543"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lisi Chen","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101533496","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0003-2129-2148"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["School of Computer Science, Nanjing University of Information Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Information Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102754146","display_name":"Shuo Shang","orcid":"https://orcid.org/0000-0002-1117-2890"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Shang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101724957","display_name":"Rui Mao","orcid":"https://orcid.org/0000-0002-3645-5520"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Mao","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000755750","display_name":"Xiangliang Zhang","orcid":"https://orcid.org/0000-0002-3574-5665"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangliang Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, IN, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5077342332"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.8714,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76230815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"35","issue":"4","first_page":"3727","last_page":"3741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10757","display_name":"Geographic Information Systems Studies","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7688291072845459},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.7106616497039795},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6284888982772827},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6226094365119934},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5582150220870972},{"id":"https://openalex.org/keywords/set-operations","display_name":"Set operations","score":0.5466970205307007},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5028757452964783},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4759102463722229},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4739546775817871},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.46508046984672546},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36007121205329895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1659751832485199},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1410805583000183},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13261958956718445},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08387675881385803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688291072845459},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.7106616497039795},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6284888982772827},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6226094365119934},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5582150220870972},{"id":"https://openalex.org/C2777168461","wikidata":"https://www.wikidata.org/wiki/Q42196253","display_name":"Set operations","level":3,"score":0.5466970205307007},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5028757452964783},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4759102463722229},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4739546775817871},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.46508046984672546},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36007121205329895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1659751832485199},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1410805583000183},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13261958956718445},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08387675881385803},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2021.3126631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3126631","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4223126646","display_name":null,"funder_award_id":"61932004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4460768019","display_name":null,"funder_award_id":"62032001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G571369483","display_name":null,"funder_award_id":"62072311","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6686603084","display_name":null,"funder_award_id":"U2001212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8078468421","display_name":null,"funder_award_id":"2020B1515120028","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1497089183","https://openalex.org/W1512794094","https://openalex.org/W1991800036","https://openalex.org/W2001700730","https://openalex.org/W2008888174","https://openalex.org/W2034466462","https://openalex.org/W2035835285","https://openalex.org/W2037562342","https://openalex.org/W2038281398","https://openalex.org/W2065259291","https://openalex.org/W2093270024","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2105436061","https://openalex.org/W2114353347","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2123427850","https://openalex.org/W2129553531","https://openalex.org/W2151930506","https://openalex.org/W2156855109","https://openalex.org/W2169387919","https://openalex.org/W2294331997","https://openalex.org/W2296107147","https://openalex.org/W2396588571","https://openalex.org/W2494566063","https://openalex.org/W2508833275","https://openalex.org/W2615658008","https://openalex.org/W2619410666","https://openalex.org/W2767135145","https://openalex.org/W2898490255","https://openalex.org/W2903672378","https://openalex.org/W2951335477","https://openalex.org/W3029266587","https://openalex.org/W4246219036","https://openalex.org/W6674576723","https://openalex.org/W6696800604"],"related_works":["https://openalex.org/W3214148052","https://openalex.org/W2151692181","https://openalex.org/W794462722","https://openalex.org/W2029625042","https://openalex.org/W4248476017","https://openalex.org/W2807741550","https://openalex.org/W2964879389","https://openalex.org/W2970426051","https://openalex.org/W1525319740","https://openalex.org/W4247864646"],"abstract_inverted_index":{"The":[0,133],"set":[1,79,113,139,174],"similarity":[2,38,117],"join":[3,39,57,73,99],"finds":[4],"all":[5],"pairs":[6,175],"of":[7,13,35,112,136,141,157],"similar":[8,151,171],"sets":[9,46,144,152],"from":[10,75],"two":[11],"collections":[12,65],"sets.":[14],"It":[15],"has":[16],"many":[17],"real":[18],"world":[19],"applications,":[20],"such":[21],"as":[22],"personalized":[23],"recommendation":[24],"and":[25,68,119,172,192,217,231],"community":[26],"mining.":[27],"In":[28,202],"this":[29,84,121,165],"paper,":[30],"we":[31,86,123,187,211],"study":[32],"the":[33,37,45,55,72,98,104,110,116,184,199,206,228,233],"problem":[34],"computing":[36],"in":[40],"a":[41,78,127,137,154,194],"dynamic":[42],"context,":[43],"where":[44],"are":[47,66],"updated":[48],"dynamically.":[49],"This,":[50],"however,":[51],"is":[52,80],"inefficient":[53],"with":[54,222],"state-of-the-art":[56],"methods,":[58],"because":[59],"they":[60],"usually":[61],"assume":[62],"that":[63,96,145,247],"data":[64],"static":[67],"have":[69],"to":[70,125,167,197,204,225,255],"compute":[71],"result":[74,100],"scratch":[76],"whenever":[77],"updated.":[81],"To":[82,181],"address":[83],"issue,":[85],"propose":[87,124,193,212],"<inline-formula><tex-math":[88,160,256],"notation=\"LaTeX\">${{\\sf":[89,161],"ALJoin}}$</tex-math></inline-formula>":[90,162],",":[91],"an":[92,213,219],"adaptive":[93],"filtering":[94,190],"approach":[95,249],"computes":[97],"incrementally":[101],"based":[102,176],"on":[103,115,120,177,208],"update":[105,158,179,229],"logs.":[106,180],"We":[107,236],"first":[108],"investigate":[109],"effect":[111],"updates":[114],"values,":[118],"basis":[122],"build":[126,183],"neighborhood":[128,134,185,234],"index":[129,135,166],"for":[130],"each":[131],"set.":[132],"specific":[138],"consists":[140],"any":[142],"other":[143],"can":[146],"be":[147],"transformed":[148],"into":[149],"its":[150],"within":[153],"threshold":[155],"number":[156],"operations.":[159],"then":[163],"uses":[164],"effectively":[168],"identify":[169],"both":[170],"dissimilar":[173],"their":[178],"efficiently":[182],"index,":[186],"devise":[188],"several":[189],"techniques":[191],"\u201clazy-forward\u201d":[195],"method":[196,239],"reduce":[198],"computational":[200],"cost.":[201],"addition,":[203],"improve":[205],"efficiency":[207],"varying":[209],"workloads,":[210],"analytical":[214],"cost":[215],"model,":[216],"design":[218],"online":[220],"algorithm":[221],"performance":[223],"guarantees":[224],"dynamically":[226],"consolidate":[227],"logs":[230],"adapt":[232],"indexes.":[235],"evaluated":[237],"our":[238,248],"using":[240],"four":[241],"real-world":[242],"datasets.":[243],"Experimental":[244],"results":[245],"show":[246],"outperforms":[250],"existing":[251],"methods":[252],"by":[253],"up":[254],"notation=\"LaTeX\">$3.7\\times$</tex-math></inline-formula>":[257],".":[258]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}