{"id":"https://openalex.org/W4379135712","doi":"https://doi.org/10.1145/3584372.3588679","title":"Weighted Minwise Hashing Beats Linear Sketching for Inner Product Estimation","display_name":"Weighted Minwise Hashing Beats Linear Sketching for Inner Product Estimation","publication_year":2023,"publication_date":"2023-06-02","ids":{"openalex":"https://openalex.org/W4379135712","doi":"https://doi.org/10.1145/3584372.3588679"},"language":"en","primary_location":{"id":"doi:10.1145/3584372.3588679","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3584372.3588679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems","raw_type":"proceedings-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/A5019389664","display_name":"Aline Bessa","orcid":"https://orcid.org/0009-0009-5486-4641"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aline Bessa","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064845272","display_name":"Majid Daliri","orcid":"https://orcid.org/0000-0003-4001-4346"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Majid Daliri","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006773757","display_name":"Juliana Freire","orcid":"https://orcid.org/0000-0003-3915-7075"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juliana Freire","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023229845","display_name":"Cameron Musco","orcid":"https://orcid.org/0000-0003-2197-6806"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cameron Musco","raw_affiliation_strings":["New York University, New York, NY, USA","University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018420180","display_name":"Christopher Musco","orcid":"https://orcid.org/0000-0002-3118-4848"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Musco","raw_affiliation_strings":["New York University, New York, NY, USA","University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101972578","display_name":"A\u00e9cio Santos","orcid":"https://orcid.org/0000-0002-5124-7770"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A\u00e9cio Santos","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100765852","display_name":"Haoxiang Zhang","orcid":"https://orcid.org/0009-0007-6939-6591"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoxiang Zhang","raw_affiliation_strings":["New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5019389664"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.5185,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7046131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9994999766349792,"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/T11106","display_name":"Data Management and Algorithms","score":0.9991999864578247,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6282176375389099},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5987959504127502},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5828117728233337},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.5211148858070374},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.518450915813446},{"id":"https://openalex.org/keywords/inner-product-space","display_name":"Inner product space","score":0.5115755200386047},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.5054256916046143},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.49907684326171875},{"id":"https://openalex.org/keywords/outer-product","display_name":"Outer product","score":0.4335615038871765},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3140168786048889},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.14164996147155762},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10488706827163696}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6282176375389099},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5987959504127502},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5828117728233337},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5211148858070374},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.518450915813446},{"id":"https://openalex.org/C91855343","wikidata":"https://www.wikidata.org/wiki/Q214159","display_name":"Inner product space","level":2,"score":0.5115755200386047},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5054256916046143},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.49907684326171875},{"id":"https://openalex.org/C180623205","wikidata":"https://www.wikidata.org/wiki/Q1268589","display_name":"Outer product","level":3,"score":0.4335615038871765},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3140168786048889},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.14164996147155762},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10488706827163696},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3584372.3588679","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3584372.3588679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1288460465","display_name":null,"funder_award_id":"ISS-2106888","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1578773895","display_name":null,"funder_award_id":"D3M program","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G2326639171","display_name":null,"funder_award_id":"2106888","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2545789077","display_name":null,"funder_award_id":"2106888,2045590,2046235","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4332126478","display_name":null,"funder_award_id":"CCF-2046235","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4848448224","display_name":null,"funder_award_id":"2046235","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1516726196","https://openalex.org/W1721994796","https://openalex.org/W1979819093","https://openalex.org/W1991800036","https://openalex.org/W1992363839","https://openalex.org/W2012833704","https://openalex.org/W2013092187","https://openalex.org/W2025051251","https://openalex.org/W2037757210","https://openalex.org/W2052207834","https://openalex.org/W2066588467","https://openalex.org/W2080745194","https://openalex.org/W2088658556","https://openalex.org/W2126907894","https://openalex.org/W2140431670","https://openalex.org/W2165612380","https://openalex.org/W2182353144","https://openalex.org/W2304387544","https://openalex.org/W2962979766","https://openalex.org/W2963673760","https://openalex.org/W2964071678","https://openalex.org/W3083028011","https://openalex.org/W4289533971"],"related_works":["https://openalex.org/W3144943409","https://openalex.org/W4254320584","https://openalex.org/W4388323020","https://openalex.org/W4246134308","https://openalex.org/W2755257841","https://openalex.org/W1510412535","https://openalex.org/W2087528975","https://openalex.org/W146094780","https://openalex.org/W4240597153","https://openalex.org/W1948977181"],"abstract_inverted_index":{"We":[0,118],"present":[1],"a":[2],"new":[3],"approach":[4,31,127],"for":[5,46,64,72,137],"independently":[6],"computing":[7],"compact":[8],"sketches":[9,132,136],"that":[10,36,125],"can":[11],"be":[12],"used":[13,103],"to":[14,104],"approximate":[15],"the":[16,26,39],"inner":[17,47,100],"product":[18,48],"between":[19,78],"pairs":[20],"of":[21,41],"high-dimensional":[22],"vectors.":[23,139],"Based":[24],"on":[25,38],"Weighted":[27],"MinHash":[28],"algorithm,":[29],"our":[30,58,120,126],"admits":[32],"strong":[33],"accuracy":[34],"guarantees":[35,40],"improve":[37],"popular":[42,95],"linear":[43,62,131],"sketching":[44,63],"approaches":[45],"estimation,":[49],"such":[50],"as":[51,90,92],"CountSketch":[52],"and":[53,110,133],"Johnson-Lindenstrauss":[54],"projection.":[55],"Specifically,":[56],"while":[57],"method":[59],"exactly":[60],"matches":[61],"dense":[65],"vectors,":[66],"it":[67],"yields":[68],"significantly":[69],"lower":[70],"error":[71],"sparse":[73,88,138],"vectors":[74,82],"with":[75],"limited":[76],"overlap":[77],"non-zero":[79],"entries.":[80],"Such":[81],"arise":[83],"in":[84,93,115],"many":[85],"applications":[86],"involving":[87,113],"data,":[89],"well":[91],"increasingly":[94],"dataset":[96],"search":[97],"applications,":[98],"where":[99],"products":[101],"are":[102],"estimate":[105],"data":[106],"covariance,":[107],"conditional":[108],"means,":[109],"other":[111],"quantities":[112],"columns":[114],"unjoined":[116],"tables.":[117],"complement":[119],"theoretical":[121],"results":[122],"by":[123],"showing":[124],"empirically":[128],"outperforms":[129],"existing":[130],"unweighted":[134],"hashing-based":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}