{"id":"https://openalex.org/W2912638695","doi":"https://doi.org/10.1109/bigdata.2018.8622279","title":"Alleviating I/O Inefficiencies to Enable Effective Model Training Over Voluminous, High-Dimensional Datasets","display_name":"Alleviating I/O Inefficiencies to Enable Effective Model Training Over Voluminous, High-Dimensional Datasets","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2912638695","doi":"https://doi.org/10.1109/bigdata.2018.8622279","mag":"2912638695"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","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/A5052776094","display_name":"Daniel Rammer","orcid":"https://orcid.org/0000-0002-4866-7547"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Rammer","raw_affiliation_strings":["Department of Computer Science, Colorado State University, Fort Collins, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Colorado State University, Fort Collins, USA","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081492255","display_name":"Walid Budgaga","orcid":null},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Walid Budgaga","raw_affiliation_strings":["Department of Computer Science, Colorado State University, Fort Collins, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Colorado State University, Fort Collins, USA","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066528786","display_name":"Thilina Buddhika","orcid":"https://orcid.org/0000-0002-1375-4595"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thilina Buddhika","raw_affiliation_strings":["Department of Computer Science, Colorado State University, Fort Collins, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Colorado State University, Fort Collins, USA","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110284766","display_name":"Shrideep Pallickara","orcid":null},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrideep Pallickara","raw_affiliation_strings":["Department of Computer Science, Colorado State University, Fort Collins, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Colorado State University, Fort Collins, USA","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072618060","display_name":"Sangmi Lee Pallickara","orcid":"https://orcid.org/0000-0001-7012-5528"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sangmi Lee Pallickara","raw_affiliation_strings":["Department of Computer Science, Colorado State University, Fort Collins, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Colorado State University, Fort Collins, USA","institution_ids":["https://openalex.org/I92446798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052776094"],"corresponding_institution_ids":["https://openalex.org/I92446798"],"apc_list":null,"apc_paid":null,"fwci":0.2089,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57915403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"468","last_page":"477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9983999729156494,"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":0.9983999729156494,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9983000159263611,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9959999918937683,"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":0.8088236451148987},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7086071372032166},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6901323795318604},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6109325289726257},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5638939738273621},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.550159215927124},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5047773122787476},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4812876582145691},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4805915057659149},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4558795988559723},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42026498913764954},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4051191210746765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31844955682754517},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11102774739265442}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8088236451148987},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7086071372032166},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6901323795318604},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6109325289726257},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5638939738273621},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.550159215927124},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5047773122787476},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4812876582145691},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4805915057659149},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4558795988559723},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42026498913764954},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4051191210746765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31844955682754517},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11102774739265442},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2018.8622279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1493892051","https://openalex.org/W2006355640","https://openalex.org/W2013344760","https://openalex.org/W2014268383","https://openalex.org/W2038157364","https://openalex.org/W2038412523","https://openalex.org/W2060393849","https://openalex.org/W2076389430","https://openalex.org/W2080234606","https://openalex.org/W2082171780","https://openalex.org/W2083842231","https://openalex.org/W2112128729","https://openalex.org/W2115975329","https://openalex.org/W2118020555","https://openalex.org/W2119391823","https://openalex.org/W2120458882","https://openalex.org/W2131975293","https://openalex.org/W2136009376","https://openalex.org/W2137515590","https://openalex.org/W2157462866","https://openalex.org/W2159128662","https://openalex.org/W2170616854","https://openalex.org/W2187384899","https://openalex.org/W2209667478","https://openalex.org/W2220196525","https://openalex.org/W2271840356","https://openalex.org/W2333507913","https://openalex.org/W2344213323","https://openalex.org/W2499761879","https://openalex.org/W2542459869","https://openalex.org/W2579247884","https://openalex.org/W2612838847","https://openalex.org/W2731931380","https://openalex.org/W2739807086","https://openalex.org/W2792678179","https://openalex.org/W2951113132","https://openalex.org/W3004511899","https://openalex.org/W3098603383","https://openalex.org/W4249843299","https://openalex.org/W4297789040","https://openalex.org/W6639805184","https://openalex.org/W6665801690","https://openalex.org/W6676770959","https://openalex.org/W6677346259","https://openalex.org/W6679815717","https://openalex.org/W6683124362","https://openalex.org/W6688670130","https://openalex.org/W6688867824","https://openalex.org/W6694517276","https://openalex.org/W6785271725","https://openalex.org/W6948342361","https://openalex.org/W6996886134"],"related_works":["https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W2140186469","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W4318559728","https://openalex.org/W3094550016","https://openalex.org/W3163198039","https://openalex.org/W4285322112","https://openalex.org/W4292794239"],"abstract_inverted_index":{"There":[0],"has":[1],"been":[2,153],"an":[3],"exponential":[4],"growth":[5],"in":[6,9],"data":[7,28,50,101],"volumes":[8],"several":[10,70,167],"domains.":[11],"Often":[12],"these":[13,90],"voluminous":[14,27],"datasets":[15,156],"encompass":[16],"a":[17,77],"large":[18],"number":[19],"of":[20,48,54,89,132,140,169],"features.":[21],"Fitting":[22],"models":[23],"to":[24,31,62,85],"such":[25],"high-dimensional,":[26],"allows":[29],"us":[30],"understand":[32],"phenomena":[33],"and":[34,57,96,100,128,162,164],"inform":[35],"decision-making.":[36],"The":[37],"analytics":[38],"process":[39],"is":[40,93,138],"naturally":[41],"iterative":[42],"as":[43],"scientists":[44],"explore":[45],"the":[46,55,58,123,133,141],"set":[47],"features,":[49],"fitting":[51],"algorithms,":[52],"portions":[53],"dataspace,":[56],"particular":[59],"algorithm's":[60],"hyperparameters":[61],"guide":[63],"their":[64],"model-building":[65,91],"process.":[66],"It":[67],"often":[68],"takes":[69],"model-fitting":[71],"attempts":[72,92],"before":[73],"one":[74],"arrives":[75],"at":[76],"satisfactory":[78],"solution":[79],"that":[80],"may":[81],"then":[82],"be":[83],"subjected":[84],"further":[86],"refinements.":[87],"Each":[88],"itself":[94],"time-consuming":[95],"dominated":[97],"by":[98,147],"I/O":[99],"movement":[102],"costs.":[103],"In":[104],"this":[105],"study,":[106],"we":[107,126,165],"present":[108],"our":[109,170],"methodology":[110],"for":[111],"significantly":[112],"alleviating":[113],"I/O-induced":[114],"inefficiencies":[115],"during":[116],"model":[117],"training.":[118],"Rather":[119],"than":[120],"work":[121,129],"with":[122,130,155],"raw":[124],"data,":[125],"generate":[127],"sketches":[131],"data.":[134],"Our":[135,149],"framework,":[136],"Fennel,":[137],"independent":[139],"libraries":[142],"or":[143],"analytical":[144],"engines":[145],"preferred":[146],"users.":[148],"empirical":[150],"benchmarks":[151],"have":[152],"performed":[154],"from":[157],"diverse":[158],"domains":[159],"(weather,":[160],"epidemiology,":[161],"music)":[163],"profile":[166],"aspects":[168],"methodology.":[171]},"counts_by_year":[{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}