{"id":"https://openalex.org/W4407356023","doi":"https://doi.org/10.1145/3709717","title":"Randomized Sketches for Quantile in LSM-tree based Store","display_name":"Randomized Sketches for Quantile in LSM-tree based Store","publication_year":2025,"publication_date":"2025-02-10","ids":{"openalex":"https://openalex.org/W4407356023","doi":"https://doi.org/10.1145/3709717"},"language":"en","primary_location":{"id":"doi:10.1145/3709717","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3709717","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3709717","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070051456","display_name":"Ziling Chen","orcid":"https://orcid.org/0009-0008-3197-2722"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziling Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-3197-2722","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084430029","display_name":"Shaoxu Song","orcid":"https://orcid.org/0000-0002-9503-2755"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoxu Song","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9503-2755","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.0464,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74793563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"3","issue":"1","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9986000061035156,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/quantile","display_name":"Quantile","score":0.8215425610542297},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5052459836006165},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4190520942211151},{"id":"https://openalex.org/keywords/environmental-science","display_name":"Environmental science","score":0.36647725105285645},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2891507148742676},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.25167787075042725},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06342142820358276}],"concepts":[{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.8215425610542297},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5052459836006165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4190520942211151},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.36647725105285645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2891507148742676},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25167787075042725},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06342142820358276}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3709717","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3709717","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3709717","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3709717","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5381224403","display_name":null,"funder_award_id":"62232005, 62021002, 92267203, 62072265","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G7348650985","display_name":null,"funder_award_id":"2021YFB3300500","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G8773551036","display_name":null,"funder_award_id":"BNR2025RC01011","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2044849727","https://openalex.org/W2068739275","https://openalex.org/W2112452856","https://openalex.org/W2123845384","https://openalex.org/W2294895103","https://openalex.org/W2575855630","https://openalex.org/W2605800201","https://openalex.org/W2613624106","https://openalex.org/W2798441769","https://openalex.org/W2798839954","https://openalex.org/W2963274201","https://openalex.org/W2963379900","https://openalex.org/W2971243175","https://openalex.org/W3014100324","https://openalex.org/W3098583838","https://openalex.org/W3100923768","https://openalex.org/W3117786929","https://openalex.org/W3146390850","https://openalex.org/W3196066353","https://openalex.org/W3197605116","https://openalex.org/W4214728981","https://openalex.org/W4255348059","https://openalex.org/W4289533942","https://openalex.org/W4301464423","https://openalex.org/W4381326806","https://openalex.org/W7139033639"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1488761988","https://openalex.org/W2044551864","https://openalex.org/W1572557500","https://openalex.org/W3124946120","https://openalex.org/W4390690393","https://openalex.org/W2047938026","https://openalex.org/W2585269888"],"abstract_inverted_index":{"Quantiles":[0],"are":[1,69,156],"costly":[2],"to":[3,31,56,83,91,158,167,196,207],"compute":[4],"exactly":[5],"but":[6],"can":[7,75],"be":[8,76,159,197],"efficiently":[9],"estimated":[10],"by":[11],"quantile":[12,40,73],"sketches.":[13],"Extensive":[14,223],"works":[15],"on":[16,25,98,225],"summarizing":[17,190,202],"streaming":[18,48,203,221],"data,":[19,100,204],"such":[20],"as":[21,78,218],"KLL":[22,188],"sketch,":[23],"focus":[24],"minimizing":[26],"the":[27,37,67,122,182,187,214,220,231,234],"cost":[28,54,86,165,211],"in":[29,44,66,118,121,152,176,219,241],"memory":[30,216],"provide":[32,92,113,135],"certain":[33],"error":[34,96,115,138],"guarantees.":[35,139],"For":[36],"problem":[38],"of":[39,42,81,105,233],"estimation":[41],"values":[43],"LSM-tree":[45,68,243],"based":[46,244],"stores,":[47],"methods":[49],"have":[50],"an":[51,163,242],"expensive":[52],"I/O":[53,85,124,164,184,210],"linear":[55,123],"data":[57,149],"size":[58,110],"N.":[59],"Since":[60],"disk":[61],"components":[62],"(chunks":[63],"and":[64,87,161,205,227],"SSTables)":[65],"immutable":[70],"once":[71],"flushed,":[72],"sketches":[74,104,133,147,172,193],"pre-computed":[77,102,192],"a":[79],"type":[80],"statistics":[82],"reduce":[84],"accelerate":[88],"queries.":[89],"Unfortunately,":[90],"deterministic":[93,103],"additive":[94,137],"\u03b5N":[95],"guarantees":[97],"queried":[99,106],"all":[101],"chunks":[107,150],"each":[108],"with":[109],"N_c":[111],"should":[112],"\u03b5N_c":[114],"guarantee,":[116],"resulting":[117],"no":[119],"improvement":[120],"cost.":[125],"In":[126],"this":[127],"study,":[128],"we":[129],"propose":[130],"pre-computing":[131],"randomized":[132,136,146,171],"which":[134,155],"Our":[140],"major":[141],"technical":[142],"contributions":[143],"include":[144],"(1)":[145],"for":[148,173],"constructed":[151,175],"flush":[153],"events,":[154,178],"proved":[157,195,206],"optimal":[160],"achieve":[162,208],"proportional":[166],"\u221a(N),":[168],"(2)":[169],"hierarchical":[170],"SSTables":[174],"compaction":[177],"that":[179,201],"further":[180],"improve":[181],"asymptotic":[183],"cost,":[185],"(3)":[186],"sketch":[189],"proposed":[191,235],"is":[194,239],"more":[198],"accurate":[199],"than":[200],"sublinear":[209],"while":[212],"achieving":[213],"same":[215],"complexity":[217],"settings.":[222],"experiments":[224],"synthetic":[226],"real":[228],"datasets":[229],"demonstrate":[230],"superiority":[232],"techniques.":[236],"The":[237],"approach":[238],"deployed":[240],"time-series":[245],"database":[246],"Apache":[247],"IoTDB.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}