{"id":"https://openalex.org/W2909578083","doi":"https://doi.org/10.1109/tpds.2019.2892765","title":"An I/O Efficient Distributed Approximation Framework Using Cluster Sampling","display_name":"An I/O Efficient Distributed Approximation Framework Using Cluster Sampling","publication_year":2019,"publication_date":"2019-01-14","ids":{"openalex":"https://openalex.org/W2909578083","doi":"https://doi.org/10.1109/tpds.2019.2892765","mag":"2909578083"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2019.2892765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2019.2892765","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5101722406","display_name":"Xuhong Zhang","orcid":"https://orcid.org/0000-0002-8571-9780"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuhong Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-8571-9780","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384682","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-0926-4761"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-0926-4761","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058611515","display_name":"Shouling Ji","orcid":"https://orcid.org/0000-0003-4268-372X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouling Ji","raw_affiliation_strings":["Institute of Cyberspace Research, College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Cyberspace Research, College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100998670","display_name":"Jiangling Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiangling Yin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431163","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0001-9048-2979"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078528016","display_name":"Xiaobo Zhou","orcid":"https://orcid.org/0000-0002-0466-7609"},"institutions":[{"id":"https://openalex.org/I888729015","display_name":"University of Colorado Colorado Springs","ror":"https://ror.org/054spjc55","country_code":"US","type":"education","lineage":["https://openalex.org/I888729015"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaobo Zhou","raw_affiliation_strings":["Department of Computer Science, University of Colorado, Colorado Springs, CO, USA"],"raw_orcid":"https://orcid.org/0000-0002-0466-7609","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Colorado, Colorado Springs, CO, USA","institution_ids":["https://openalex.org/I888729015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066099338","display_name":"Changjun Jiang","orcid":"https://orcid.org/0000-0003-0637-9317"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changjun Jiang","raw_affiliation_strings":["Tongji University, Shanghai Shi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai Shi, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":0.4922,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70665824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"30","issue":"7","first_page":"1494","last_page":"1511"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9986000061035156,"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":0.9986000061035156,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9923999905586243,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9922000169754028,"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/computer-science","display_name":"Computer science","score":0.8387276530265808},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5730140209197998},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.552621066570282},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5526066422462463},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5390365123748779},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4971452057361603},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4441553056240082},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.4249740242958069},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32100045680999756},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.24740594625473022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20246478915214539},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.10039865970611572},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0944487452507019}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8387276530265808},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5730140209197998},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.552621066570282},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5526066422462463},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5390365123748779},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4971452057361603},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4441553056240082},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.4249740242958069},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32100045680999756},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.24740594625473022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20246478915214539},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.10039865970611572},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0944487452507019},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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:10.1109/tpds.2019.2892765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2019.2892765","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G1611999932","display_name":null,"funder_award_id":"CCF-1337244","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G2705367118","display_name":null,"funder_award_id":"1717388","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G7021125818","display_name":null,"funder_award_id":"61772466","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8244423146","display_name":null,"funder_award_id":"1527249","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1441763937","https://openalex.org/W1493915708","https://openalex.org/W1964404845","https://openalex.org/W1976597724","https://openalex.org/W1977785821","https://openalex.org/W1989269499","https://openalex.org/W1991418309","https://openalex.org/W2024562752","https://openalex.org/W2041912938","https://openalex.org/W2046804949","https://openalex.org/W2065280033","https://openalex.org/W2071989194","https://openalex.org/W2077346647","https://openalex.org/W2080374925","https://openalex.org/W2094031870","https://openalex.org/W2099601885","https://openalex.org/W2103212156","https://openalex.org/W2122949840","https://openalex.org/W2124181495","https://openalex.org/W2141403362","https://openalex.org/W2150915951","https://openalex.org/W2157851816","https://openalex.org/W2164507334","https://openalex.org/W2293019624","https://openalex.org/W2346956847","https://openalex.org/W2429510775","https://openalex.org/W2436533802","https://openalex.org/W2506776957","https://openalex.org/W2578054369","https://openalex.org/W2799873608","https://openalex.org/W6628361010","https://openalex.org/W6629475768"],"related_works":["https://openalex.org/W2494523064","https://openalex.org/W2943623134","https://openalex.org/W2030292806","https://openalex.org/W2215759665","https://openalex.org/W2960358116","https://openalex.org/W3041172967","https://openalex.org/W2749065928","https://openalex.org/W2147155098","https://openalex.org/W4287727129","https://openalex.org/W4281381431"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,106,161,179,204,227,247],"present":[4],"an":[5,229,243,275],"I/O":[6,92,150],"efficient":[7,151,194],"distributed":[8,100,139,257],"approximation":[9,61,244,264],"framework":[10],"to":[11,22,121,148,166,174,188,233,297],"support":[12,207],"approximations":[13,211],"on":[14,98,282],"arbitrary":[15],"sub-datasets":[16,173],"of":[17,27,47,77,86,125,132,145,171],"a":[18,44,78,87,108,126,133,163,175,190,198,237,256,293],"large":[19],"dataset.":[20],"Due":[21],"the":[23,51,55,73,104,123,138,168,181,222,250,300],"prohibitive":[24],"storage":[25,75],"overhead":[26],"caching":[28],"offline":[29,35],"samples":[30,65],"for":[31,42,83,193,197],"each":[32,129],"sub-dataset,":[33],"existing":[34],"sample-based":[36,60],"systems":[37],"provide":[38],"high":[39],"accuracy":[40,97],"results":[41,287],"only":[43],"limited":[45],"number":[46,170],"sub-datasets,":[48],"such":[49,146,212],"as":[50,213,274],"popular":[52],"ones.":[53],"On":[54],"other":[56],"hand,":[57],"current":[58],"online":[59,152,195],"systems,":[62],"which":[63],"generate":[64],"at":[66,128],"runtime,":[67],"do":[68],"not":[69],"take":[70],"into":[71,272],"account":[72],"uneven":[74],"distribution":[76,85,109],"sub-dataset.":[79],"They":[80],"work":[81],"well":[82],"uniform":[84],"sub-dataset":[88,127],"while":[89],"suffer":[90],"low":[91],"efficiency":[93],"and":[94,141,215,266,278],"poor":[95],"estimation":[96,220],"unevenly":[99],"sub-datasets.":[101,202],"To":[102],"address":[103],"problem,":[105],"develop":[107,162],"aware":[110],"method":[111,192],"called":[112],"CLAP":[113,206,232,271,290],"(cluster":[114],"sampling":[115,183,196,252],"based":[116,219],"approximation).":[117],"Our":[118,284],"idea":[119],"is":[120],"collect":[122],"occurrences":[124],"logical":[130],"partition":[131],"dataset":[134],"(storage":[135],"distribution)":[136],"in":[137,158,231,255],"system,":[140],"make":[142],"good":[143],"use":[144],"information":[147],"enable":[149],"sampling.":[153],"There":[154],"are":[155],"three":[156],"thrusts":[157],"CLAP.":[159],"First,":[160],"probabilistic":[164],"map":[165],"reduce":[167],"exponential":[169],"recorded":[172],"linear":[176],"one.":[177],"Second,":[178],"apply":[180],"cluster":[182],"with":[184,208,263],"unequal":[185],"probability":[186],"theory":[187],"implement":[189],"distribution-aware":[191],"single":[199],"or":[200],"multiple":[201],"Third,":[203],"enrich":[205],"more":[209],"complex":[210],"ratio":[214],"regression":[216],"using":[217],"bootstrap":[218],"beyond":[221],"simple":[223],"aggragation":[224],"approxiamtions.":[225],"Forth,":[226],"add":[228],"option":[230],"allow":[234],"users":[235],"specifying":[236],"target":[238],"error":[239],"bound":[240],"when":[241],"submitting":[242],"job.":[245],"Fifth,":[246],"quantitatively":[248],"derive":[249],"optimal":[251],"unit":[253],"size":[254],"file":[258],"system":[259,277],"by":[260,295],"associating":[261],"it":[262,281],"costs":[265],"accuracy.":[267],"We":[268],"have":[269],"implemented":[270],"Hadoop":[273],"example":[276],"open":[279],"sourced":[280],"GitHub.":[283],"comprehensive":[285],"experimental":[286],"show":[288],"that":[289],"can":[291],"achieve":[292],"speedup":[294],"up":[296],"20\u00d7":[298],"over":[299],"precise":[301],"execution.":[302]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}