{"id":"https://openalex.org/W1999702719","doi":"https://doi.org/10.1145/2487575.2487677","title":"Big data analytics with small footprint","display_name":"Big data analytics with small footprint","publication_year":2013,"publication_date":"2013-08-11","ids":{"openalex":"https://openalex.org/W1999702719","doi":"https://doi.org/10.1145/2487575.2487677","mag":"1999702719"},"language":"en","primary_location":{"id":"doi:10.1145/2487575.2487677","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2487575.2487677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5089723214","display_name":"John Canny","orcid":"https://orcid.org/0000-0002-7161-7927"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Canny","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046520437","display_name":"Huasha Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huasha Zhao","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":9.3111,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.98588334,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"9","issue":null,"first_page":"95","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9965999722480774,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8625390529632568},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6450172662734985},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6270238757133484},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.46536019444465637},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.46255674958229065},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4613059163093567},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.43695613741874695},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.41480278968811035},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.4123757779598236},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3816741108894348},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35034194588661194},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2756311893463135},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2210879921913147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8625390529632568},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6450172662734985},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6270238757133484},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46536019444465637},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.46255674958229065},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4613059163093567},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.43695613741874695},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.41480278968811035},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.4123757779598236},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3816741108894348},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35034194588661194},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2756311893463135},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2210879921913147},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2487575.2487677","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2487575.2487677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W78077100","https://openalex.org/W114517082","https://openalex.org/W1525651898","https://openalex.org/W1880262756","https://openalex.org/W1976860187","https://openalex.org/W1986966428","https://openalex.org/W2041517243","https://openalex.org/W2044849727","https://openalex.org/W2054141820","https://openalex.org/W2070786785","https://openalex.org/W2105767123","https://openalex.org/W2125993116","https://openalex.org/W2131975293","https://openalex.org/W2142623206","https://openalex.org/W2169724035","https://openalex.org/W2172249709","https://openalex.org/W2184623761","https://openalex.org/W2407746682","https://openalex.org/W2951113132","https://openalex.org/W4248240383","https://openalex.org/W4285719527","https://openalex.org/W6639619044","https://openalex.org/W6686239164"],"related_works":["https://openalex.org/W4231704780","https://openalex.org/W2083794993","https://openalex.org/W352609212","https://openalex.org/W4200340037","https://openalex.org/W1511772879","https://openalex.org/W3137434606","https://openalex.org/W4372263373","https://openalex.org/W4396520111","https://openalex.org/W2929170389","https://openalex.org/W4300097863"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,57,67,71,126,155],"BID":[4],"Data":[5],"Suite,":[6],"a":[7,74,108,121],"collection":[8],"of":[9,28,54,66,128,143],"hardware,":[10],"software":[11],"and":[12,61,82,99,102,136],"design":[13,49,76],"patterns":[14,139],"that":[15,36,78,96,112,124],"enable":[16],"fast,":[17],"large-scale":[18],"data":[19,72,87],"mining":[20,88],"at":[21],"very":[22,114],"low":[23],"cost.":[24],"By":[25],"co-designing":[26],"all":[27],"these":[29],"elements":[30,65,157],"we":[31],"achieve":[32],"single-machine":[33],"performance":[34,142],"levels":[35],"equal":[37],"or":[38],"exceed":[39],"reported":[40],"cluster":[41],"implementations":[42],"for":[43,85,164],"common":[44],"benchmark":[45,150],"problems.":[46],"A":[47],"key":[48],"criterion":[50],"is":[51,59],"rapid":[52],"exploration":[53],"models,":[55],"hence":[56],"system":[58,111],"interactive":[60,93],"primarily":[62],"single-user.":[63],"The":[64],"suite":[68],"are:":[69],"(i)":[70],"engine,":[73],"hardware":[75],"pattern":[77],"balances":[79],"storage,":[80],"CPU":[81,98],"GPU":[83,100],"acceleration":[84,101],"typical":[86],"workloads,":[89],"(ii)":[90],"BIDMat,":[91],"an":[92],"matrix":[94],"library":[95],"integrates":[97],"novel":[103],"computational":[104],"kernels":[105],"(iii),":[106],"BIDMach,":[107],"machine":[109],"learning":[110],"includes":[113],"efficient":[115],"model":[116,130],"optimizers,":[117],"(iv)":[118],"Butterfly":[119],"mixing,":[120],"communication":[122],"strategy":[123],"hides":[125],"latency":[127],"frequent":[129],"updates":[131],"needed":[132],"by":[133],"fast":[134],"optimizers":[135],"(v)":[137],"Design":[138],"to":[140,152,159],"improve":[141],"iterative":[144],"update":[145],"algorithms.":[146],"We":[147],"present":[148],"several":[149],"problems":[151],"show":[153],"how":[154],"above":[156],"combine":[158],"yield":[160],"multiple":[161],"orders-of-magnitude":[162],"improvements":[163],"each":[165],"problem.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}