{"id":"https://openalex.org/W2796341401","doi":"https://doi.org/10.1145/3269206.3271690","title":"Engineering a Simplified 0-Bit Consistent Weighted Sampling","display_name":"Engineering a Simplified 0-Bit Consistent Weighted Sampling","publication_year":2018,"publication_date":"2018-10-17","ids":{"openalex":"https://openalex.org/W2796341401","doi":"https://doi.org/10.1145/3269206.3271690","mag":"2796341401"},"language":"en","primary_location":{"id":"doi:10.1145/3269206.3271690","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3269206.3271690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1804.00069","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Edward Raff","orcid":null},"institutions":[{"id":"https://openalex.org/I1322124587","display_name":"Booz Allen Hamilton (United States)","ror":"https://ror.org/051rcp357","country_code":"US","type":"company","lineage":["https://openalex.org/I1322124587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Raff","raw_affiliation_strings":["Booz Allen Hamilton, Columbia, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Booz Allen Hamilton, Columbia, MD, USA","institution_ids":["https://openalex.org/I1322124587"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jared Sylvester","orcid":null},"institutions":[{"id":"https://openalex.org/I1322124587","display_name":"Booz Allen Hamilton (United States)","ror":"https://ror.org/051rcp357","country_code":"US","type":"company","lineage":["https://openalex.org/I1322124587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jared Sylvester","raw_affiliation_strings":["Booz Allen Hamilton, Columbia, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Booz Allen Hamilton, Columbia, MD, USA","institution_ids":["https://openalex.org/I1322124587"]}]},{"author_position":"last","author":{"id":null,"display_name":"Charles Nicholas","orcid":null},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Nicholas","raw_affiliation_strings":["University of Maryland, Baltimore County, Catonsville, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County, Catonsville, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.212,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.53742758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1203","last_page":"1212"},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9908999800682068,"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/sketch","display_name":"Sketch","score":0.7730000019073486},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5184999704360962},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4756999909877777},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46650001406669617},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.32600000500679016}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.7730000019073486},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5184999704360962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4903999865055084},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4447000026702881},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3991999924182892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35339999198913574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3400000035762787},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25760000944137573},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3269206.3271690","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3269206.3271690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.00069","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.00069","pdf_url":"https://arxiv.org/pdf/1804.00069","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1804.00069","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.00069","pdf_url":"https://arxiv.org/pdf/1804.00069","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1999092742","https://openalex.org/W2018175892","https://openalex.org/W2097865464","https://openalex.org/W2123427850","https://openalex.org/W2126907894","https://openalex.org/W2145349611","https://openalex.org/W2152565070","https://openalex.org/W2162006472","https://openalex.org/W2604248105","https://openalex.org/W2608296545","https://openalex.org/W2742475488","https://openalex.org/W2766353929"],"related_works":[],"abstract_inverted_index":{"The":[0,78],"Min-Hashing":[1],"approach":[2,30,60,82],"to":[3,20,61,68,74],"sketching":[4],"has":[5,26],"become":[6,27],"an":[7,105],"important":[8],"tool":[9],"in":[10],"data":[11],"analysis,":[12],"information":[13],"retrial,":[14],"and":[15,35,89],"classification.":[16],"To":[17],"apply":[18],"it":[19],"real-valued":[21],"datasets,":[22],"the":[23,50,62,75,98],"ICWS":[24,44,63],"algorithm":[25],"a":[28,46,57],"seminal":[29],"that":[31,65,92],"is":[32,83],"widely":[33],"used,":[34],"provides":[36],"state-of-the-art":[37],"performance":[38],"for":[39],"this":[40],"problem":[41],"space.":[42],"However,":[43],"suffers":[45],"computational":[47],"burden":[48],"as":[49],"sketch":[51],"size":[52],"K":[53],"increases.":[54],"We":[55],"develop":[56],"new":[58,94],"Simplified":[59,95],"algorithm,":[64],"enables":[66],"us":[67],"obtain":[69],"over":[70],"20x":[71],"speedups":[72],"compared":[73],"standard":[76],"algorithm.":[77],"veracity":[79],"of":[80,101,107],"our":[81,93],"demonstrated":[84],"empirically":[85],"on":[86],"multiple":[87],"datasets":[88],"scenarios,":[90],"showing":[91],"CWS":[96],"obtains":[97],"same":[99],"quality":[100],"results":[102],"while":[103],"being":[104],"order":[106],"magnitude":[108],"faster.":[109]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2018-04-13T00:00:00"}