{"id":"https://openalex.org/W2796436043","doi":"https://doi.org/10.1109/tkde.2020.2981311","title":"HyperMinHash: MinHash in LogLog space","display_name":"HyperMinHash: MinHash in LogLog space","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W2796436043","doi":"https://doi.org/10.1109/tkde.2020.2981311","mag":"2796436043","pmid":"https://pubmed.ncbi.nlm.nih.gov/38288326"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2020.2981311","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2020.2981311","pdf_url":"https://ieeexplore.ieee.org/ielx7/69/4358933/09039684.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/69/4358933/09039684.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015501574","display_name":"Yun William Yu","orcid":"https://orcid.org/0000-0002-8275-9576"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yun William Yu","raw_affiliation_strings":["Department of Mathematics, University of Toronto, Toronto, Ontario, Canada M5S 2E4"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Toronto, Toronto, Ontario, Canada M5S 2E4","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023500196","display_name":"Griffin M. Weber","orcid":"https://orcid.org/0000-0002-2597-881X"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Griffin M. Weber","raw_affiliation_strings":["Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":{"value":2045,"currency":"USD","value_usd":2045},"fwci":0.2844,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65934855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":"34","issue":"1","first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9990000128746033,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9990000128746033,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.9955000281333923,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.992900013923645,"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/jaccard-index","display_name":"Jaccard index","score":0.8698583841323853},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.6132302284240723},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.5037400126457214},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.44482406973838806},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3694979250431061},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3480292558670044},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25902971625328064},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.258370041847229}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8698583841323853},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.6132302284240723},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.5037400126457214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44482406973838806},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3694979250431061},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3480292558670044},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25902971625328064},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.258370041847229},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/tkde.2020.2981311","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2020.2981311","pdf_url":"https://ieeexplore.ieee.org/ielx7/69/4358933/09039684.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmid:38288326","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38288326","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"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:arXiv.org:1710.08436","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.08436","pdf_url":"https://arxiv.org/pdf/1710.08436","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"pmh:oai:pubmedcentral.nih.gov:10824537","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10824537","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10824537/pdf/nihms-1959518.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Knowl Data Eng","raw_type":"Text"},{"id":"mag:2796436043","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1710.08436.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1710.08436","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1710.08436","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.1109/tkde.2020.2981311","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2020.2981311","pdf_url":"https://ieeexplore.ieee.org/ielx7/69/4358933/09039684.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2981891787","display_name":null,"funder_award_id":"U01CA198934","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G3234351459","display_name":null,"funder_award_id":"U01CA198934","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G4355748215","display_name":null,"funder_award_id":"U54-HG007963","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G7399544069","display_name":"Patient-Centered Information Commons","funder_award_id":"3u54hg007963-05s1","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7466737494","display_name":"Visualizing healthcare system dynamics in biomedical Big Data","funder_award_id":"5u01ca198934-03","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2796436043.pdf","grobid_xml":"https://content.openalex.org/works/W2796436043.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W194932104","https://openalex.org/W1574338450","https://openalex.org/W1785933978","https://openalex.org/W1859017491","https://openalex.org/W1998840390","https://openalex.org/W2011737794","https://openalex.org/W2060536778","https://openalex.org/W2099480861","https://openalex.org/W2103126020","https://openalex.org/W2106120011","https://openalex.org/W2132069633","https://openalex.org/W2134212491","https://openalex.org/W2140431670","https://openalex.org/W2144982963","https://openalex.org/W2147017814","https://openalex.org/W2221439497","https://openalex.org/W2479183965","https://openalex.org/W2531371138","https://openalex.org/W2592374036","https://openalex.org/W2593397259","https://openalex.org/W2719363210","https://openalex.org/W3141706065","https://openalex.org/W4245504068","https://openalex.org/W6639231921","https://openalex.org/W6682042839","https://openalex.org/W6734131497","https://openalex.org/W6740087195","https://openalex.org/W6929990038"],"related_works":["https://openalex.org/W3011980846","https://openalex.org/W3018746117","https://openalex.org/W2574633002","https://openalex.org/W1551247056","https://openalex.org/W2981639848","https://openalex.org/W2147935317","https://openalex.org/W2944298321","https://openalex.org/W1947022961","https://openalex.org/W2027244654","https://openalex.org/W2999295646","https://openalex.org/W2951544251","https://openalex.org/W2776892647","https://openalex.org/W3013848899","https://openalex.org/W2121028531","https://openalex.org/W2949961440","https://openalex.org/W1999058046","https://openalex.org/W2107082304","https://openalex.org/W1705602972","https://openalex.org/W2950962175","https://openalex.org/W2603759229"],"abstract_inverted_index":{"In":[0],"this":[1],"extended":[2],"abstract,":[3],"we":[4,32,36],"describe":[5],"and":[6,72],"analyze":[7],"a":[8,39,46,76,80,85],"lossy":[9],"compression":[10],"of":[11,15,19,49,68,105,116,122],"MinHash":[12,124],"from":[13],"buckets":[14,18],"size$O(\\log":[16,20],"n)$to":[17],"\\log":[21,92,95],"n)$by":[22],"encoding":[23],"using":[24,120],"floating-point":[25],"notation.":[26],"This":[27],"new":[28],"compressed":[29],"sketch,":[30],"which":[31],"call":[33],"HyperMinHash,":[34],"as":[35,45,61],"build":[37],"off":[38],"HyperLogLog":[40],"scaffold,":[41],"can":[42,125],"be":[43],"used":[44],"drop-in":[47],"replacement":[48],"MinHash.":[50],"Unlike":[51],"comparable":[52],"Jaccard":[53,81,103,128],"index":[54],"fingerprinting":[55],"algorithms":[56],"in":[57],"sub-logarithmic":[58],"space":[59],"(such":[60],"b-bit":[62],"MinHash),":[63],"HyperMinHash":[64,88,100],"retains":[65],"MinHash's":[66],"features":[67],"streaming":[69],"updates,":[70],"unions,":[71],"cardinality":[73],"estimation.":[74],"For":[75],"additive":[77],"approximation":[78],"error$\\epsilon$on":[79],"index$":[82],"t$,":[83],"given":[84],"random":[86],"oracle,":[87],"needs$O\\left(\\epsilon":[89],"^{-2}":[90],"\\left(\\log":[91],"n":[93],"+":[94],"\\frac{1}{":[96],"\\epsilon":[97],"}":[98],"\\right)\\right)$space.":[99],"allows":[101],"estimating":[102],"indices":[104,129],"0.01":[106],"for":[107,130],"set":[108],"cardinalities":[109,131],"on":[110],"the":[111,133],"order":[112],"of$10^{19}$with":[113],"relative":[114],"error":[115],"around":[117],"10":[118],"percent":[119],"2MiB":[121],"memory;":[123],"only":[126],"estimate":[127],"of$10^{10}$with":[132],"same":[134],"memory":[135],"consumption.":[136]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}