{"id":"https://openalex.org/W3023186600","doi":"https://doi.org/10.1145/3358960.3379144","title":"A Sampling-Based Tool for Scaling Graph Datasets","display_name":"A Sampling-Based Tool for Scaling Graph Datasets","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3023186600","doi":"https://doi.org/10.1145/3358960.3379144","mag":"3023186600"},"language":"en","primary_location":{"id":"doi:10.1145/3358960.3379144","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3358960.3379144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/SPEC International Conference on Performance Engineering","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/A5067588255","display_name":"Ahmed Musaafir","orcid":null},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Ahmed Musaafir","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056738388","display_name":"Alexandru Uta","orcid":"https://orcid.org/0000-0001-5477-2194"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alexandru Uta","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053039691","display_name":"Henk Dreuning","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Henk Dreuning","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087297053","display_name":"Ana-Lucia Varbanescu","orcid":"https://orcid.org/0000-0002-4932-1900"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]},{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ana-Lucia Varbanescu","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067588255"],"corresponding_institution_ids":["https://openalex.org/I865915315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9998999834060669,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9988999962806702,"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":0.9977999925613403,"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":0.75867760181427},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6082121133804321},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5703995823860168},{"id":"https://openalex.org/keywords/clustering-coefficient","display_name":"Clustering coefficient","score":0.5336977243423462},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5168564915657043},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5105150938034058},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4892091751098633},{"id":"https://openalex.org/keywords/power-graph-analysis","display_name":"Power graph analysis","score":0.4392291009426117},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4288373589515686},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4040423631668091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16114389896392822},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14983224868774414}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75867760181427},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6082121133804321},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5703995823860168},{"id":"https://openalex.org/C22047676","wikidata":"https://www.wikidata.org/wiki/Q898680","display_name":"Clustering coefficient","level":3,"score":0.5336977243423462},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5168564915657043},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5105150938034058},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4892091751098633},{"id":"https://openalex.org/C106937863","wikidata":"https://www.wikidata.org/wiki/Q7236518","display_name":"Power graph analysis","level":3,"score":0.4392291009426117},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4288373589515686},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4040423631668091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16114389896392822},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14983224868774414},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3358960.3379144","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3358960.3379144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/98d4de19-ecdf-44e4-b0cf-74224b5460da","is_oa":false,"landing_page_url":"https://research.vu.nl/en/publications/98d4de19-ecdf-44e4-b0cf-74224b5460da","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Musaafir , A , Uta , A , Dreuning , H & Varbanescu , A L 2020 , A sampling-based tool for scaling graph datasets . in ICPE '20 : Proceedings of the ACM/SPEC International Conference on Performance Engineering . Association for Computing Machinery, Inc , pp. 289-300 , 11th ACM/SPEC International Conference on Performance Engineering, ICPE 2020 , Edmonton , Canada , 20/04/20 . https://doi.org/10.1145/3358960.3379144","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:research.vu.nl:publications/98d4de19-ecdf-44e4-b0cf-74224b5460da","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/citedby.url?scp=85085949431&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Musaafir , A , Uta , A , Dreuning , H & Varbanescu , A L 2020 , A sampling-based tool for scaling graph datasets . in ICPE '20 : Proceedings of the ACM/SPEC International Conference on Performance Engineering . Association for Computing Machinery, Inc , pp. 289-300 , 11th ACM/SPEC International Conference on Performance Engineering, ICPE 2020 , Edmonton , Canada , 20/04/20 . https://doi.org/10.1145/3358960.3379144","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W131619556","https://openalex.org/W1482680420","https://openalex.org/W1588530906","https://openalex.org/W1783256592","https://openalex.org/W1998003984","https://openalex.org/W2028897509","https://openalex.org/W2077443691","https://openalex.org/W2146008005","https://openalex.org/W2157520633","https://openalex.org/W2294347342","https://openalex.org/W2295258302","https://openalex.org/W2404670603","https://openalex.org/W2500091015","https://openalex.org/W2515464413","https://openalex.org/W2546689575","https://openalex.org/W2547085757","https://openalex.org/W2577407133","https://openalex.org/W2755088640","https://openalex.org/W2899482689","https://openalex.org/W2964153721","https://openalex.org/W3004555699","https://openalex.org/W6713680192"],"related_works":["https://openalex.org/W2755787904","https://openalex.org/W2892694839","https://openalex.org/W4400134723","https://openalex.org/W2054462038","https://openalex.org/W4376224899","https://openalex.org/W2791749053","https://openalex.org/W2001615711","https://openalex.org/W3132826944","https://openalex.org/W3205845529","https://openalex.org/W2758539126"],"abstract_inverted_index":{"Graph":[0],"processing":[1,147,193],"has":[2],"become":[3],"a":[4,15,59,63,105,159,179],"topic":[5],"of":[6,17,62,76,107,140,145,158,162,191],"interest":[7],"in":[8],"many":[9],"domains.":[10],"However,":[11],"we":[12,44,67,175],"still":[13],"observe":[14],"lack":[16],"representative":[18],"datasets":[19,141],"for":[20,37,48,118,142,187],"in-depth":[21,143,188],"performance":[22,189],"and":[23,35,91],"scalability":[24],"analysis.":[25,39],"Neither":[26],"data":[27],"collections,":[28],"nor":[29],"graph":[30,108,121,146,192],"generators":[31],"provide":[32,58,68,138],"enough":[33],"diversity":[34],"control":[36,101],"thorough":[38],"To":[40],"address":[41],"this":[42],"problem,":[43],"proposea":[45],"heuristic":[46],"method":[47,127],"scaling":[49],"existing":[50],"graphs.":[51],"Our":[52,149],"approach,":[53],"based":[54],"onsampling":[55],"andinterconnection,":[56],"can":[57,133,184],"scaled":[60,78,156,182],"\"version\"":[61],"given":[64],"graph.":[65],"Moreover,":[66],"analytical":[69],"models":[70],"to":[71,96,136],"predict":[72],"the":[73,77,82,88,94,120],"topological":[74],"properties":[75,165],"graphs":[79,157,183],"(such":[80],"as":[81,128],"diameter,":[83],"degree":[84],"distribution,":[85],"density,":[86],"or":[87],"clustering":[89],"coefficient),":[90],"further":[92,124],"enable":[93],"user":[95,172],"tweak":[97],"these":[98],"properties.":[99],"Property":[100],"is":[102],"achieved":[103],"through":[104,178],"portfolio":[106],"interconnection":[109],"methods":[110],"(e.g.,":[111],"star,":[112],"ring,":[113],"chain,":[114],"fully":[115],"connected)":[116],"applied":[117],"combining":[119],"samples.":[122],"We":[123],"implement":[125],"our":[126,153],"an":[129],"open-source":[130],"tool":[131,154],"which":[132],"be":[134,185],"used":[135,186],"quickly":[137],"families":[139],"benchmarking":[144],"algorithms.":[148,194],"empirical":[150],"evaluation":[151],"demonstrates":[152],"provides":[155],"wide":[160],"range":[161],"sizes,":[163],"whose":[164],"match":[166],"well":[167],"with":[168],"model":[169],"predictions":[170],"and/or":[171],"requirements.":[173],"Finally,":[174],"also":[176],"illustrate,":[177],"case-study,":[180],"how":[181],"analysis":[190]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}