{"id":"https://openalex.org/W2593265540","doi":"https://doi.org/10.14778/3137628.3137651","title":"On sampling from massive graph streams","display_name":"On sampling from massive graph streams","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2593265540","doi":"https://doi.org/10.14778/3137628.3137651","mag":"2593265540"},"language":"en","primary_location":{"id":"doi:10.14778/3137628.3137651","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3137628.3137651","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","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/A5059294839","display_name":"Nesreen K. Ahmed","orcid":"https://orcid.org/0000-0002-7913-4962"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nesreen K. Ahmed","raw_affiliation_strings":["Intel Labs"],"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048558842","display_name":"Nick Duffield","orcid":"https://orcid.org/0000-0001-7211-1584"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nick Duffield","raw_affiliation_strings":["Texas A&M University"],"affiliations":[{"raw_affiliation_string":"Texas A&M University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038113815","display_name":"Theodore L. Willke","orcid":"https://orcid.org/0000-0001-9825-513X"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Theodore L. Willke","raw_affiliation_strings":["Intel Labs"],"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009957887","display_name":"Ryan A. Rossi","orcid":"https://orcid.org/0000-0001-9758-0635"},"institutions":[{"id":"https://openalex.org/I173498003","display_name":"Palo Alto Research Center","ror":"https://ror.org/0529fxt39","country_code":"US","type":"facility","lineage":["https://openalex.org/I173498003","https://openalex.org/I4210132870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan A. Rossi","raw_affiliation_strings":["Palo Alto Research Center"],"affiliations":[{"raw_affiliation_string":"Palo Alto Research Center","institution_ids":["https://openalex.org/I173498003"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059294839"],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":9.4944,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.98300569,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"10","issue":"11","first_page":"1430","last_page":"1441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9926999807357788,"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"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9926999807357788,"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"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9876000285148621,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9876000285148621,"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/estimator","display_name":"Estimator","score":0.6647318005561829},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5303348302841187},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5015957355499268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48704150319099426},{"id":"https://openalex.org/keywords/global-positioning-system","display_name":"Global Positioning System","score":0.4623485803604126},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4077492654323578},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3862684369087219},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.28062155842781067},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2125881314277649},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.08839336037635803}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6647318005561829},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5303348302841187},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5015957355499268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48704150319099426},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.4623485803604126},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4077492654323578},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3862684369087219},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28062155842781067},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2125881314277649},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.08839336037635803},{"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:10.14778/3137628.3137651","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3137628.3137651","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1602844557","https://openalex.org/W1647106508","https://openalex.org/W1761167196","https://openalex.org/W1965972569","https://openalex.org/W1967172267","https://openalex.org/W1979819093","https://openalex.org/W1982682305","https://openalex.org/W1994473607","https://openalex.org/W2019420194","https://openalex.org/W2031082424","https://openalex.org/W2034417563","https://openalex.org/W2037774459","https://openalex.org/W2042631176","https://openalex.org/W2055245094","https://openalex.org/W2068936568","https://openalex.org/W2085845250","https://openalex.org/W2094308804","https://openalex.org/W2102322109","https://openalex.org/W2119885577","https://openalex.org/W2124450885","https://openalex.org/W2141403143","https://openalex.org/W2150191781","https://openalex.org/W2152092514","https://openalex.org/W2154191591","https://openalex.org/W2163557584","https://openalex.org/W2165753192","https://openalex.org/W2241571695","https://openalex.org/W2278390984","https://openalex.org/W2294347342","https://openalex.org/W2440288152","https://openalex.org/W2585003791","https://openalex.org/W2752853835","https://openalex.org/W2752885492","https://openalex.org/W2951660554","https://openalex.org/W2963316155","https://openalex.org/W4230058301","https://openalex.org/W4232440580","https://openalex.org/W4239726656","https://openalex.org/W4242068677","https://openalex.org/W4285719527","https://openalex.org/W6637685275","https://openalex.org/W6669417358","https://openalex.org/W7029321148"],"related_works":["https://openalex.org/W3162200841","https://openalex.org/W2586280620","https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2805505483","https://openalex.org/W2384744344","https://openalex.org/W1799694159","https://openalex.org/W2393169196","https://openalex.org/W2366610330","https://openalex.org/W1550496571"],"abstract_inverted_index":{"We":[0,91,189,200],"propose":[1,92],"Graph":[2],"Priority":[3],"Sampling":[4],"(":[5],"gps":[6,19,81,101,120,214,249],"),":[7],"a":[8,21,104,143,158,202,229,240,262],"new":[9,144],"paradigm":[10],"for":[11,222,246],"order-based":[12],"reservoir":[13],"sampling":[14,27,54,79,87,180],"from":[15,209],"massive":[16],"graph":[17,42,78,112,148,234],"streams.":[18],"provides":[20],"general":[22],"way":[23],"to":[24,29,36,61,99,102,109,118,121,186,195],"weight":[25],"edge":[26,53,86,162],"according":[28],"auxiliary":[30],"and/or":[31],"size":[32],"variables":[33],"so":[34,59],"as":[35,60,157],"accomplish":[37],"various":[38,210],"estimation":[39,64,94,178],"goals":[40],"of":[41,47,66,68,71,85,107,137,147,160,177,232,239,265,268],"properties.":[43],"In":[44,73],"the":[45,63,83,129,173,233,269,273],"context":[46],"subgraph":[48,89,130,138,154],"counting,":[49,226],"we":[50],"show":[51],"how":[52],"weights":[55],"can":[56],"be":[57],"chosen":[58],"minimize":[62],"variance":[65,124],"counts":[67,255],"specified":[69],"sets":[70],"subgraphs.":[72],"distinction":[74],"with":[75,193,218,235,256],"many":[76],"prior":[77],"schemes,":[80],"separates":[82],"functions":[84],"and":[88,114,179,197,212,224,253],"estimation.":[90],"two":[93],"frameworks:":[95],"(1)":[96],"Post-Stream":[97],"estimation,":[98,117],"allow":[100,119],"construct":[103],"reference":[105],"sample":[106],"edges":[108,271],"support":[110],"retrospective":[111],"queries,":[113],"(2)":[115],"In-Stream":[116],"obtain":[122],"lower":[123],"estimates":[125,132,251],"by":[126],"incrementally":[127],"updating":[128],"count":[131],"during":[133],"stream":[134,149],"processing.":[135],"Unbiasedness":[136],"estimators":[139],"is":[140],"established":[141],"through":[142],"Martingale":[145],"formulation":[146],"order":[150],"sampling,":[151],"in":[152,172,272],"which":[153],"estimators,":[155,163],"written":[156],"product":[159],"constituent":[161],"are":[164],"unbiased,":[165],"even":[166],"when":[167],"computed":[168],"at":[169],"different":[170],"points":[171],"stream.":[174],"The":[175],"separation":[176],"enables":[181],"significant":[182],"resource":[183],"savings":[184],"relative":[185],"previous":[187],"work.":[188],"illustrate":[190],"our":[191],"framework":[192],"applications":[194],"triangle":[196,223,252],"wedge":[198,225,254],"counting.":[199],"perform":[201],"large-scale":[203],"experimental":[204],"study":[205],"on":[206],"real-world":[207],"graphs":[208],"domains":[211],"types.":[213],"achieves":[215],"high":[216],"accuracy":[217],"<":[219,257,266],"1%":[220,258],"error":[221],"while":[227,260],"storing":[228,261],"small":[230,263],"fraction":[231,264],"average":[236],"update":[237],"times":[238],"few":[241],"microseconds":[242],"per":[243],"edge.":[244],"Notably,":[245],"billion-scale":[247],"graphs,":[248],"accurately":[250],"error,":[259],"0.01%":[267],"total":[270],"graph.":[274]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}