{"id":"https://openalex.org/W2984000064","doi":"https://doi.org/10.1145/3357384.3358124","title":"A Sampling-Based System for Approximate Big Data Analysis on Computing Clusters","display_name":"A Sampling-Based System for Approximate Big Data Analysis on Computing Clusters","publication_year":2019,"publication_date":"2019-11-03","ids":{"openalex":"https://openalex.org/W2984000064","doi":"https://doi.org/10.1145/3357384.3358124","mag":"2984000064"},"language":"en","primary_location":{"id":"doi:10.1145/3357384.3358124","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3358124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge 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/A5064798504","display_name":"Salman Salloum","orcid":"https://orcid.org/0000-0002-6750-003X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Salman Salloum","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046627853","display_name":"Yinxu Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinxu Wu","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003347359","display_name":"Joshua Zhexue Huang","orcid":"https://orcid.org/0000-0002-6797-2571"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Joshua Zhexue Huang","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5331,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70119837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2481","last_page":"2484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9977999925613403,"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":0.9977999925613403,"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/T11106","display_name":"Data Management and Algorithms","score":0.9902999997138977,"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":0.9886999726295471,"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/big-data","display_name":"Big data","score":0.8901875615119934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8072528839111328},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7102522253990173},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5279459357261658},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.509088933467865},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4915502965450287},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.45518937706947327},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4515588879585266},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.44266921281814575},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.4310492277145386},{"id":"https://openalex.org/keywords/data-intensive-computing","display_name":"Data-intensive computing","score":0.42409682273864746},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32535701990127563},{"id":"https://openalex.org/keywords/grid-computing","display_name":"Grid computing","score":0.1204635500907898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11181604862213135},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.100200355052948}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8901875615119934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072528839111328},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7102522253990173},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5279459357261658},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.509088933467865},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4915502965450287},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.45518937706947327},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4515588879585266},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.44266921281814575},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.4310492277145386},{"id":"https://openalex.org/C76831024","wikidata":"https://www.wikidata.org/wiki/Q5227096","display_name":"Data-intensive computing","level":4,"score":0.42409682273864746},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32535701990127563},{"id":"https://openalex.org/C70429105","wikidata":"https://www.wikidata.org/wiki/Q249999","display_name":"Grid computing","level":3,"score":0.1204635500907898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11181604862213135},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.100200355052948},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3357384.3358124","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3357384.3358124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1965706740","https://openalex.org/W1975184797","https://openalex.org/W2036816792","https://openalex.org/W2071989194","https://openalex.org/W2081930221","https://openalex.org/W2150915951","https://openalex.org/W2155806188","https://openalex.org/W2173213060","https://openalex.org/W2339488751","https://openalex.org/W2542459869","https://openalex.org/W2773612851","https://openalex.org/W2788617251","https://openalex.org/W2963100393"],"related_works":["https://openalex.org/W1980895735","https://openalex.org/W109851046","https://openalex.org/W1977658424","https://openalex.org/W3004288367","https://openalex.org/W2520913399","https://openalex.org/W154510354","https://openalex.org/W2371047563","https://openalex.org/W1004551674","https://openalex.org/W2010981565","https://openalex.org/W4238448430"],"abstract_inverted_index":{"To":[0],"break":[1],"the":[2,38,66,125,162,169,188],"in-memory":[3],"bottleneck":[4],"and":[5,31,58,62,109,138,155,185],"facilitate":[6],"online":[7,53,175],"sampling":[8,176],"in":[9,90,115],"cluster":[10,42],"computing":[11,25,43,168],"frameworks,":[12],"we":[13,132],"propose":[14],"a":[15,77,82,103,112,116,134],"new":[16,67,179],"sampling-based":[17],"system":[18,137,180],"for":[19,124],"approximate":[20,122,153],"big":[21,35,45,48,51,55,59,78,182],"data":[22,36,46,49,52,56,60,73,79,88,127,171,183,190],"analysis":[23,186],"on":[24],"clusters.":[26],"We":[27,64],"address":[28],"both":[29],"computational":[30],"statistical":[32],"aspects":[33],"of":[34,41,84,164],"across":[37],"main":[39],"layers":[40],"frameworks:":[44],"storage,":[47],"management,":[50],"sampling,":[54],"processing,":[57],"exploration":[61,184],"analysis.":[63],"use":[65],"Random":[68],"Sample":[69],"Partition":[70],"(RSP)":[71],"distributed":[72,117],"model":[74],"to":[75,120,151],"store":[76],"set":[80,83,191],"as":[81,158,160],"ready-to-use":[85],"random":[86],"sample":[87],"blocks":[89,106,147],"Hadoop":[91],"Distributed":[92],"File":[93],"System":[94],"(HDFS),":[95],"called":[96],"RSP":[97,105,146],"blocks.":[98],"With":[99],"this":[100,130],"system,":[101],"only":[102],"few":[104],"are":[107],"selected":[108],"processed":[110],"using":[111],"sequential":[113],"algorithm":[114],"data-parallel":[118],"manner":[119],"produce":[121],"results":[123],"entire":[126,170,189],"set.":[128],"In":[129],"paper,":[131],"present":[133],"prototype":[135],"RSP-based":[136],"demonstrate":[139],"its":[140],"advantages.":[141],"Our":[142],"experiments":[143],"show":[144],"that":[145],"can":[148],"be":[149,193],"used":[150],"get":[152],"models":[154],"summary":[156],"statistics":[157],"well":[159],"estimate":[161],"proportions":[163],"inconsistent":[165],"values":[166],"without":[167],"or":[172],"running":[173],"expensive":[174],"operations.":[177],"This":[178],"enables":[181],"where":[187],"cannot":[192],"computed.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}