{"id":"https://openalex.org/W3009800626","doi":"https://doi.org/10.1145/3366423.3380069","title":"LSF-Join: Locality Sensitive Filtering for Distributed All-Pairs Set Similarity Under Skew","display_name":"LSF-Join: Locality Sensitive Filtering for Distributed All-Pairs Set Similarity Under Skew","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3009800626","doi":"https://doi.org/10.1145/3366423.3380069","mag":"3009800626"},"language":"en","primary_location":{"id":"doi:10.1145/3366423.3380069","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380069","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3366423.3380069","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066091408","display_name":"Cyrus Rashtchian","orcid":"https://orcid.org/0000-0001-9422-2779"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I4210140792","display_name":"Universidad Cat\u00f3lica Santo Domingo","ror":"https://ror.org/04ytq6y86","country_code":"DO","type":"education","lineage":["https://openalex.org/I4210140792"]}],"countries":["DO","US"],"is_corresponding":true,"raw_author_name":"Cyrus Rashtchian","raw_affiliation_strings":["UCSD","University of California\u2014San Diego"],"affiliations":[{"raw_affiliation_string":"UCSD","institution_ids":["https://openalex.org/I4210140792"]},{"raw_affiliation_string":"University of California\u2014San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101979342","display_name":"Aneesh Sharma","orcid":"https://orcid.org/0009-0002-5252-7376"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aneesh Sharma","raw_affiliation_strings":["Google","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102861589","display_name":"David P. Woodruff","orcid":"https://orcid.org/0000-0002-2158-1380"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Woodruff","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066091408"],"corresponding_institution_ids":["https://openalex.org/I36258959","https://openalex.org/I4210140792"],"apc_list":null,"apc_paid":null,"fwci":0.0981,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36673537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2998","last_page":"3004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11478","display_name":"Caching and Content Delivery","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/T11106","display_name":"Data Management and Algorithms","score":0.9929999709129333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.7188656330108643},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.690906822681427},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.6552003026008606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6502094268798828},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.622089684009552},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.5544527769088745},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5535979270935059},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5385881662368774},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.530206561088562},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5065985918045044},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.5025227069854736},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4550545811653137},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.45089155435562134},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42251256108283997},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41445812582969666},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.38652509450912476},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.33952581882476807},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2497929036617279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22059175372123718},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.16449549794197083},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.159354567527771},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.1213105320930481},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10352745652198792}],"concepts":[{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.7188656330108643},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.690906822681427},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6552003026008606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6502094268798828},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.622089684009552},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.5544527769088745},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5535979270935059},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5385881662368774},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.530206561088562},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5065985918045044},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.5025227069854736},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4550545811653137},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45089155435562134},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42251256108283997},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41445812582969666},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.38652509450912476},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.33952581882476807},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2497929036617279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22059175372123718},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.16449549794197083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.159354567527771},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1213105320930481},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10352745652198792},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3366423.3380069","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380069","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2003.02972","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.02972","pdf_url":"https://arxiv.org/pdf/2003.02972","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":"doi:10.48550/arxiv.2003.02972","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.02972","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3009800626","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3366423.3380069","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380069","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1736726159","https://openalex.org/W1998067572","https://openalex.org/W2008199814","https://openalex.org/W2051586153","https://openalex.org/W2062008074","https://openalex.org/W2065259291","https://openalex.org/W2080234606","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2121269638","https://openalex.org/W2125671345","https://openalex.org/W2130305366","https://openalex.org/W2137139422","https://openalex.org/W2137373960","https://openalex.org/W2151930506","https://openalex.org/W2152526152","https://openalex.org/W2169387919","https://openalex.org/W2396588571","https://openalex.org/W2397770138","https://openalex.org/W2407585166","https://openalex.org/W2521888566","https://openalex.org/W2564448502","https://openalex.org/W2566913073","https://openalex.org/W2592901506","https://openalex.org/W2619410666","https://openalex.org/W2755088640","https://openalex.org/W2791946429","https://openalex.org/W2798412430","https://openalex.org/W2883952940","https://openalex.org/W2938070826","https://openalex.org/W2963174348","https://openalex.org/W2963535486","https://openalex.org/W2963886823","https://openalex.org/W2963940951","https://openalex.org/W2964013013","https://openalex.org/W2978452900","https://openalex.org/W3105727767","https://openalex.org/W4289258909"],"related_works":["https://openalex.org/W3012776781","https://openalex.org/W2963886823","https://openalex.org/W1488303220","https://openalex.org/W2903672378","https://openalex.org/W2963535486","https://openalex.org/W2883280339","https://openalex.org/W2592901506","https://openalex.org/W2798412430","https://openalex.org/W2619410666","https://openalex.org/W2169795703","https://openalex.org/W3099795033","https://openalex.org/W2584499795","https://openalex.org/W2900972923","https://openalex.org/W2250382098","https://openalex.org/W2147033904","https://openalex.org/W2964613948","https://openalex.org/W2796483994","https://openalex.org/W2356914479","https://openalex.org/W2430378630","https://openalex.org/W2465997604"],"abstract_inverted_index":{"All-pairs":[0],"set":[1,118],"similarity":[2,17,164],"is":[3,79,125],"a":[4,28,55,70,110,126],"widely":[5],"used":[6],"data":[7],"mining":[8],"task,":[9],"even":[10,63,161],"for":[11,26,100,115,162,167],"large":[12,101],"and":[13,166,178,183],"high-dimensional":[14],"datasets.":[15],"Traditionally,":[16],"search":[18],"has":[19,38],"focused":[20],"on":[21,69,131,147,174,190],"discovering":[22,43],"very":[23,90],"similar":[24],"pairs,":[25,160],"which":[27,144],"variety":[29],"of":[30,42,45,73,122,181],"efficient":[31],"algorithms":[32],"are":[33,85,89,145],"known.":[34],"However,":[35],"recent":[36],"work":[37],"highlighted":[39],"the":[40,175],"importance":[41],"pairs":[44],"sets":[46],"with":[47],"relatively":[48],"small":[49,71,163],"intersection":[50],"sizes.":[51,103],"For":[52],"example,":[53],"in":[54],"recommender":[56],"system,":[57],"two":[58,94],"users":[59],"may":[60],"be":[61],"alike":[62],"though":[64],"their":[65],"interests":[66],"only":[67],"overlap":[68],"percentage":[72],"items.":[74],"In":[75,135],"such":[76],"systems,":[77],"it":[78],"also":[80,185],"common":[81],"that":[82,154],"some":[83],"dimensions":[84],"highly-skewed,":[86],"because":[87],"they":[88],"popular.":[91],"Together,":[92],"these":[93],"properties":[95],"render":[96],"previous":[97],"approaches":[98],"infeasible":[99],"input":[102,169],"To":[104],"address":[105],"this":[106],"problem,":[107],"we":[108,152,184],"present":[109],"new":[111],"distributed":[112],"algorithm,":[113],"LSF-Join,":[114,182],"approximate":[116,142],"all-pairs":[117],"similarity.":[119],"The":[120],"core":[121],"our":[123,137],"algorithm":[124],"randomized":[127],"selection":[128],"procedure":[129],"based":[130,146],"Locality":[132,148],"Sensitive":[133,149],"Filtering.":[134],"particular,":[136],"method":[138],"deviates":[139],"from":[140],"prior":[141],"algorithms,":[143],"Hashing.":[150],"Theoretically,":[151],"show":[153],"LSF-Join":[155],"efficiently":[156],"finds":[157],"most":[158],"close":[159],"thresholds":[165],"skewed":[168],"sets.":[170],"We":[171],"prove":[172],"guarantees":[173],"communication,":[176],"work,":[177],"maximum":[179],"load":[180],"experimentally":[186],"demonstrate":[187],"its":[188],"accuracy":[189],"multiple":[191],"graphs.":[192]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}