{"id":"https://openalex.org/W2124701120","doi":"https://doi.org/10.1145/2623330.2630811","title":"Sampling for big data","display_name":"Sampling for big data","publication_year":2014,"publication_date":"2014-08-22","ids":{"openalex":"https://openalex.org/W2124701120","doi":"https://doi.org/10.1145/2623330.2630811","mag":"2124701120"},"language":"en","primary_location":{"id":"doi:10.1145/2623330.2630811","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2630811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5031896681","display_name":"Graham Cormode","orcid":"https://orcid.org/0000-0002-0698-0922"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Graham Cormode","raw_affiliation_strings":["University of Warwick, Coventry, United Kingdom","University of Warwick Coventry , United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick, Coventry, United Kingdom","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"University of Warwick Coventry , United Kingdom","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048558842","display_name":"Nick Duffield","orcid":"https://orcid.org/0000-0001-7211-1584"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nick Duffield","raw_affiliation_strings":["Rutgers University, Piscataway, NJ, USA","Rutgers University , Piscataway, NJ , USA ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Rutgers University , Piscataway, NJ , USA ,","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1975","last_page":"1975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9979000091552734,"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/T11478","display_name":"Caching and Content Delivery","score":0.9979000091552734,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9936000108718872,"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":0.8739362955093384},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6950090527534485},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5811807513237},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5283523201942444},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5224915146827698},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5023219585418701},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48926374316215515},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4169835150241852},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4146740734577179},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37068110704421997},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2993655800819397},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11037668585777283}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8739362955093384},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6950090527534485},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5811807513237},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5283523201942444},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5224915146827698},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5023219585418701},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48926374316215515},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4169835150241852},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4146740734577179},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37068110704421997},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2993655800819397},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11037668585777283},{"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2623330.2630811","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2630811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:elartu.tntu.edu.ua:lib/40264","is_oa":false,"landing_page_url":"http://elartu.tntu.edu.ua/handle/lib/40264","pdf_url":null,"source":{"id":"https://openalex.org/S4306401453","display_name":"ELARTU (Ternopil National Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I92130990","host_organization_name":"Ternopil Ivan Pul'uj National Technical University","host_organization_lineage":["https://openalex.org/I92130990"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Abstract"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2018821139","https://openalex.org/W2124701120","https://openalex.org/W2148598618","https://openalex.org/W2419017369","https://openalex.org/W2980728347","https://openalex.org/W3047623425","https://openalex.org/W3193381039"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W4233347783","https://openalex.org/W2910064364","https://openalex.org/W4255224757","https://openalex.org/W2499527417"],"abstract_inverted_index":{"One":[0],"response":[1],"to":[2,10,14,61,109,135],"the":[3,18,57,71,75,85,93,111,114],"proliferation":[4],"of":[5,45,59,74,107,113],"large":[6,125],"datasets":[7,64],"has":[8],"been":[9],"develop":[11],"ingenious":[12],"ways":[13],"throw":[15],"resources":[16],"at":[17],"problem,":[19],"using":[20],"massive":[21],"fault":[22],"tolerant":[23],"storage":[24],"architectures,":[25],"parallel":[26],"and":[27,35,47,69,92,129,139],"graphical":[28],"computation":[29],"models":[30],"such":[31],"as":[32],"MapReduce,":[33],"Pregel":[34],"Giraph.":[36],"However,":[37],"not":[38,48],"all":[39,49],"environments":[40],"can":[41],"support":[42,66],"this":[43],"scale":[44],"resources,":[46],"queries":[50],"need":[51],"an":[52],"exact":[53],"response.":[54],"This":[55,117],"motivates":[56],"use":[58],"sampling":[60,82,100,136],"generate":[62],"summary":[63],"that":[65],"rapid":[67],"queries,":[68],"prolong":[70],"useful":[72],"life":[73],"data":[76,90],"in":[77,99,121],"storage.":[78],"To":[79],"be":[80],"effective,":[81],"must":[83],"mediate":[84],"tensions":[86],"between":[87],"resource":[88],"constraints,":[89],"characteristics,":[91],"required":[94],"query":[95],"accuracy.":[96],"The":[97],"state-of-the-art":[98],"goes":[101],"far":[102],"beyond":[103],"simple":[104],"uniform":[105],"selection":[106],"elements,":[108],"maximize":[110],"usefulness":[112],"resulting":[115],"sample.":[116],"tutorial":[118],"reviews":[119],"progress":[120],"sample":[122],"design":[123],"for":[124],"datasets,":[126],"including":[127],"streaming":[128],"graph-structured":[130],"data.":[131],"Applications":[132],"are":[133],"discussed":[134],"network":[137],"traffic":[138],"social":[140],"networks.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
