{"id":"https://openalex.org/W2622662334","doi":"https://doi.org/10.1145/3085504.3085514","title":"Bi-Level Online Aggregation on Raw Data","display_name":"Bi-Level Online Aggregation on Raw Data","publication_year":2017,"publication_date":"2017-06-05","ids":{"openalex":"https://openalex.org/W2622662334","doi":"https://doi.org/10.1145/3085504.3085514","mag":"2622662334"},"language":"en","primary_location":{"id":"doi:10.1145/3085504.3085514","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3085504.3085514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Scientific and Statistical Database Management","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/A5027563812","display_name":"Yu Cheng","orcid":"https://orcid.org/0000-0002-2619-4398"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Cheng","raw_affiliation_strings":["Turn, Inc. and UC Merced"],"affiliations":[{"raw_affiliation_string":"Turn, Inc. and UC Merced","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075541712","display_name":"Weijie Zhao","orcid":"https://orcid.org/0000-0003-0967-1436"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weijie Zhao","raw_affiliation_strings":["University of California Merced"],"affiliations":[{"raw_affiliation_string":"University of California Merced","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065838987","display_name":"Florin Rusu","orcid":"https://orcid.org/0000-0002-7018-9043"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florin Rusu","raw_affiliation_strings":["University of California Merced"],"affiliations":[{"raw_affiliation_string":"University of California Merced","institution_ids":["https://openalex.org/I156087764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027563812"],"corresponding_institution_ids":["https://openalex.org/I156087764"],"apc_list":null,"apc_paid":null,"fwci":1.6822,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85161643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9994000196456909,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9990000128746033,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8506224155426025},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.6997697949409485},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.66392582654953},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.661878228187561},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.49755290150642395},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4941292107105255},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4904601275920868},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4768739342689514},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.40174421668052673},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3769657611846924},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1656339466571808},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14356517791748047},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.0974423885345459},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08760318160057068},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07877439260482788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8506224155426025},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.6997697949409485},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.66392582654953},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.661878228187561},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.49755290150642395},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4941292107105255},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4904601275920868},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4768739342689514},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.40174421668052673},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3769657611846924},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1656339466571808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14356517791748047},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0974423885345459},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08760318160057068},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07877439260482788},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3085504.3085514","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3085504.3085514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Conference on Scientific and Statistical Database Management","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":47,"referenced_works":["https://openalex.org/W1586825695","https://openalex.org/W1593503233","https://openalex.org/W2002791618","https://openalex.org/W2010150096","https://openalex.org/W2016443758","https://openalex.org/W2019386158","https://openalex.org/W2020147322","https://openalex.org/W2022858489","https://openalex.org/W2027748129","https://openalex.org/W2035801804","https://openalex.org/W2041912938","https://openalex.org/W2043097023","https://openalex.org/W2050810837","https://openalex.org/W2064777887","https://openalex.org/W2066293100","https://openalex.org/W2083751237","https://openalex.org/W2099601885","https://openalex.org/W2103207352","https://openalex.org/W2110363867","https://openalex.org/W2113601246","https://openalex.org/W2119072946","https://openalex.org/W2119885577","https://openalex.org/W2120113238","https://openalex.org/W2132808937","https://openalex.org/W2136014429","https://openalex.org/W2151065878","https://openalex.org/W2151892596","https://openalex.org/W2155970976","https://openalex.org/W2156964798","https://openalex.org/W2161692763","https://openalex.org/W2162569193","https://openalex.org/W2164507334","https://openalex.org/W2165990006","https://openalex.org/W2167811976","https://openalex.org/W2218458026","https://openalex.org/W2293308125","https://openalex.org/W2296677182","https://openalex.org/W2394680079","https://openalex.org/W2421547754","https://openalex.org/W2429510775","https://openalex.org/W2436406362","https://openalex.org/W2438261314","https://openalex.org/W2498260651","https://openalex.org/W2521416656","https://openalex.org/W2586736480","https://openalex.org/W2912802084","https://openalex.org/W4229903866"],"related_works":["https://openalex.org/W4213239787","https://openalex.org/W4377131110","https://openalex.org/W2114337652","https://openalex.org/W2046590706","https://openalex.org/W2791738351","https://openalex.org/W2084395052","https://openalex.org/W3024941504","https://openalex.org/W2034771340","https://openalex.org/W646678958","https://openalex.org/W181005589"],"abstract_inverted_index":{"In-situ":[0],"processing":[1,35],"has":[2,59],"been":[3,60],"proposed":[4],"as":[5,62,90,92],"a":[6,37,80,107],"novel":[7],"data":[8,67],"exploration":[9,68],"solution":[10],"in":[11],"many":[12],"domains":[13],"generating":[14],"massive":[15],"amounts":[16],"of":[17,33,46,52,79,111],"raw":[18,29],"data,":[19],"e.g.,":[20],"astronomy,":[21],"since":[22],"it":[23],"provides":[24],"immediate":[25],"SQL":[26],"querying":[27],"over":[28],"files.":[30],"The":[31],"performance":[32],"in-situ":[34],"across":[36],"query":[38],"workload":[39],"is,":[40],"however,":[41],"limited":[42],"by":[43,74],"the":[44,53,77,83,93,116],"speed":[45],"full":[47],"scan,":[48],"tokenizing,":[49],"and":[50],"parsing":[51],"entire":[54],"data.":[55,117],"Online":[56],"aggregation":[57],"(OLA)":[58],"introduced":[61],"an":[63],"efficient":[64],"method":[65],"for":[66],"that":[69],"identifies":[70],"uninteresting":[71],"patterns":[72],"faster":[73],"continuously":[75],"estimating":[76],"result":[78],"computation":[81,86],"during":[82],"actual":[84],"processing---the":[85],"can":[87],"be":[88,99],"stopped":[89],"early":[91],"estimate":[94],"is":[95],"accurate":[96],"enough":[97],"to":[98],"deemed":[100],"uninteresting.":[101],"However,":[102],"existing":[103],"OLA":[104],"solutions":[105],"have":[106],"high":[108],"upfront":[109],"cost":[110],"randomly":[112],"shuffling":[113],"and/or":[114],"sampling":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}