{"id":"https://openalex.org/W4406495605","doi":"https://doi.org/10.1109/bigdata62323.2024.10826029","title":"Key Compression Limits for k-Minimum Value Sketches","display_name":"Key Compression Limits for k-Minimum Value Sketches","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406495605","doi":"https://doi.org/10.1109/bigdata62323.2024.10826029"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10826029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10826029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5037434711","display_name":"Charlie Dickens","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Charlie Dickens","raw_affiliation_strings":["Yahoo!"],"affiliations":[{"raw_affiliation_string":"Yahoo!","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107784127","display_name":"Eric Bax","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Bax","raw_affiliation_strings":["Yahoo!"],"affiliations":[{"raw_affiliation_string":"Yahoo!","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107784128","display_name":"Alexander Saydakov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Saydakov","raw_affiliation_strings":["Yahoo!"],"affiliations":[{"raw_affiliation_string":"Yahoo!","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037434711"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":0.3663,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66291761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"338","last_page":"343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9909999966621399,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9909999966621399,"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9779000282287598,"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/key","display_name":"Key (lock)","score":0.7021371126174927},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5718621015548706},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5010373592376709},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4391523003578186},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4267596900463104},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14595937728881836},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.13190728425979614},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08119803667068481},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.06043654680252075}],"concepts":[{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7021371126174927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5718621015548706},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5010373592376709},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4391523003578186},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4267596900463104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14595937728881836},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13190728425979614},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08119803667068481},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.06043654680252075},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10826029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10826029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1607198972","https://openalex.org/W1785933978","https://openalex.org/W1979819093","https://openalex.org/W1982092405","https://openalex.org/W1995875735","https://openalex.org/W2005731313","https://openalex.org/W2011737794","https://openalex.org/W2025051251","https://openalex.org/W2097865464","https://openalex.org/W2099480861","https://openalex.org/W2103126020","https://openalex.org/W2116241780","https://openalex.org/W2144982963","https://openalex.org/W2613751718","https://openalex.org/W2749679580","https://openalex.org/W2752908210","https://openalex.org/W2951602119","https://openalex.org/W2963699114","https://openalex.org/W2993415324","https://openalex.org/W3011980846","https://openalex.org/W3129989568","https://openalex.org/W3169136406","https://openalex.org/W3183020571","https://openalex.org/W4214495955","https://openalex.org/W4290944102","https://openalex.org/W4403160497","https://openalex.org/W4406495605","https://openalex.org/W6637601118","https://openalex.org/W6743322848","https://openalex.org/W6790684161"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"The":[0],"k-Minimum":[1],"Values":[2],"(KMV)":[3],"data":[4,55],"sketch":[5],"algorithm":[6],"stores":[7],"the":[8,16,28,48,54,76,85,125],"k":[9,77],"least":[10,78],"hash":[11],"keys":[12,29],"generated":[13],"by":[14],"hashing":[15],"items":[17],"in":[18,41,53,117],"a":[19,95,98],"dataset.":[20],"We":[21,57,131],"show":[22,59,105],"that":[23,60,84,103,106,113,133,143],"compression":[24,74,138],"based":[25,128],"on":[26,129],"ordering":[27],"and":[30,111,140,149],"encoding":[31,86],"successive":[32],"differences":[33],"can":[34],"offer":[35],"O(log":[36,61],"n)":[37,62],"bits":[38,64],"per":[39,66],"key":[40,67],"expected":[42,63],"storage":[43],"savings,":[44],"where":[45],"n":[46,80],"is":[47,68,88,108,119,145],"number":[49],"of":[50,73,79,124],"unique":[51],"values":[52,82],"set.":[56],"also":[58],"saved":[65],"optimal":[69],"for":[70,75],"any":[71],"form":[72],"random":[81],"\u2013":[83],"method":[87,100,135],"near-optimal":[89],"among":[90],"all":[91],"methods":[92],"to":[93,101],"encode":[94],"KMVsketch.We":[96],"present":[97],"practical":[99],"perform":[102],"compression,":[104],"it":[107,144],"computationally":[109],"efficient,":[110],"demonstrate":[112,142],"its":[114],"average":[115],"savings":[116],"practice":[118],"within":[120],"about":[121],"five":[122],"percent":[123],"theoretical":[126],"minimum":[127],"entropy.":[130],"verify":[132],"our":[134],"outperforms":[136],"off-the-shelf":[137],"methods,":[139],"we":[141],"practical,":[146],"using":[147],"real":[148],"synthetic":[150],"data.<sup":[151],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[152],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[153]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}