{"id":"https://openalex.org/W4392454245","doi":"https://doi.org/10.14778/3636218.3636238","title":"FusionFlow: Accelerating Data Preprocessing for Machine Learning with CPU-GPU Cooperation","display_name":"FusionFlow: Accelerating Data Preprocessing for Machine Learning with CPU-GPU Cooperation","publication_year":2023,"publication_date":"2023-12-01","ids":{"openalex":"https://openalex.org/W4392454245","doi":"https://doi.org/10.14778/3636218.3636238"},"language":"en","primary_location":{"id":"doi:10.14778/3636218.3636238","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3636218.3636238","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/A5100605439","display_name":"Taeyoon Kim","orcid":"https://orcid.org/0000-0002-5060-5302"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Taeyoon Kim","raw_affiliation_strings":["UNIST"],"affiliations":[{"raw_affiliation_string":"UNIST","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053954141","display_name":"ChanHo Park","orcid":null},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"ChanHo Park","raw_affiliation_strings":["UNIST"],"affiliations":[{"raw_affiliation_string":"UNIST","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004547897","display_name":"Mansur Mukimbekov","orcid":null},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mansur Mukimbekov","raw_affiliation_strings":["UNIST"],"affiliations":[{"raw_affiliation_string":"UNIST","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100576745","display_name":"Heelim Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heelim Hong","raw_affiliation_strings":["UNIST"],"affiliations":[{"raw_affiliation_string":"UNIST","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332530","display_name":"Minseok Kim","orcid":"https://orcid.org/0000-0003-1675-8003"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minseok Kim","raw_affiliation_strings":["UNIST"],"affiliations":[{"raw_affiliation_string":"UNIST","institution_ids":["https://openalex.org/I48566637"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103029944","display_name":"Ze Jin","orcid":"https://orcid.org/0000-0003-3379-5113"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ze Jin","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104172871","display_name":"Changdae Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changdae Kim","raw_affiliation_strings":["ETRI"],"affiliations":[{"raw_affiliation_string":"ETRI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059352538","display_name":"Ji-Yong Shin","orcid":"https://orcid.org/0000-0002-1595-4849"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Ji-Yong Shin","raw_affiliation_strings":["Northeastern University"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079046832","display_name":"Myeongjae Jeon","orcid":"https://orcid.org/0000-0002-0748-6627"},"institutions":[{"id":"https://openalex.org/I48566637","display_name":"Ulsan National Institute of Science and Technology","ror":"https://ror.org/017cjz748","country_code":"KR","type":"education","lineage":["https://openalex.org/I48566637"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myeongjae Jeon","raw_affiliation_strings":["UNIST"],"affiliations":[{"raw_affiliation_string":"UNIST","institution_ids":["https://openalex.org/I48566637"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100605439"],"corresponding_institution_ids":["https://openalex.org/I48566637"],"apc_list":null,"apc_paid":null,"fwci":0.9839,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78797238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"17","issue":"4","first_page":"863","last_page":"876"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9990000128746033,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9976999759674072,"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":0.7699096202850342},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7367681264877319},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5958855152130127},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5436964631080627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3403453826904297},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3362959325313568}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699096202850342},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7367681264877319},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5958855152130127},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5436964631080627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3403453826904297},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3362959325313568}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3636218.3636238","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3636218.3636238","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W398859631","https://openalex.org/W1442374986","https://openalex.org/W1528469369","https://openalex.org/W2117539524","https://openalex.org/W2132737349","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2340222647","https://openalex.org/W2489529491","https://openalex.org/W2734941459","https://openalex.org/W2747329762","https://openalex.org/W2765170276","https://openalex.org/W2806187986","https://openalex.org/W2910100551","https://openalex.org/W2919594608","https://openalex.org/W2949736877","https://openalex.org/W2969388332","https://openalex.org/W2970971581","https://openalex.org/W2977730164","https://openalex.org/W2994088087","https://openalex.org/W3011751313","https://openalex.org/W3012479151","https://openalex.org/W3012514909","https://openalex.org/W3043413334","https://openalex.org/W3094004195","https://openalex.org/W3104414677","https://openalex.org/W3105067168","https://openalex.org/W3106998729","https://openalex.org/W3118004751","https://openalex.org/W3121562065","https://openalex.org/W3134621603","https://openalex.org/W3138327474","https://openalex.org/W3138959866","https://openalex.org/W3177263144","https://openalex.org/W3182050489","https://openalex.org/W3182301081","https://openalex.org/W3196732841","https://openalex.org/W4212774754","https://openalex.org/W4226479682","https://openalex.org/W4281657584","https://openalex.org/W4288083516","https://openalex.org/W4318718888","https://openalex.org/W4323343904","https://openalex.org/W4381328603","https://openalex.org/W4387031932","https://openalex.org/W4401588497","https://openalex.org/W6684859321","https://openalex.org/W6762334975","https://openalex.org/W6772167297","https://openalex.org/W6774321293","https://openalex.org/W6794531325","https://openalex.org/W6810832814","https://openalex.org/W6983393456"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,23,87],"enhances":[2],"the":[3,76,85,111,122,125,147],"accuracy":[4],"of":[5,15,80,113,121],"DL":[6,81,158],"models":[7],"by":[8,117,169],"diversifying":[9],"training":[10,82,151,178],"samples":[11],"through":[12],"a":[13,65,132],"sequence":[14],"data":[16,22,77,86,91],"transformations.":[17],"While":[18],"recent":[19],"advancements":[20],"in":[21,171],"have":[24],"demonstrated":[25],"remarkable":[26],"efficacy,":[27],"they":[28],"often":[29],"rely":[30],"on":[31,146],"computationally":[32],"expensive":[33],"and":[34,54,72,96,142,156],"dynamic":[35,133],"algorithms.":[36],"Unfortunately,":[37],"current":[38],"system":[39,66],"optimizations,":[40],"primarily":[41],"designed":[42],"to":[43,52,74,149,175,185],"leverage":[44],"CPUs,":[45],"cannot":[46],"effectively":[47,109],"support":[48],"these":[49,60],"methods":[50,168],"due":[51],"costs":[53],"limited":[55],"resource":[56],"availability.":[57],"To":[58],"address":[59],"issues,":[61],"we":[62],"introduce":[63],"FusionFlow,":[64],"that":[67,83,163],"cooperatively":[68],"utilizes":[69],"both":[70,154],"CPUs":[71,95,183],"GPUs":[73,97],"accelerate":[75],"preprocessing":[78,92],"stage":[79],"runs":[84],"algorithm.":[88],"FusionFlow":[89,130,164],"orchestrates":[90],"tasks":[93,123,137],"across":[94],"while":[98],"minimizing":[99],"interference":[100],"with":[101,138],"GPU-based":[102],"model":[103],"training.":[104],"In":[105],"doing":[106],"so,":[107],"it":[108],"mitigates":[110],"risk":[112],"GPU":[114],"memory":[115,119],"overflow":[116],"managing":[118],"allocations":[120],"within":[124],"GPU-wide":[126],"free":[127],"space.":[128],"Furthermore,":[129],"provides":[131],"scheduling":[134],"strategy":[135],"for":[136,153],"varying":[139],"computational":[140],"demands":[141],"reallocates":[143],"compute":[144,188],"resources":[145,189],"fly":[148],"enhance":[150],"throughput":[152],"single":[155],"multi-GPU":[157],"jobs.":[159],"Our":[160],"evaluations":[161],"show":[162],"outperforms":[165],"existing":[166],"CPU-based":[167],"16--285%":[170],"single-machine":[172],"scenarios":[173],"and,":[174],"achieve":[176],"similar":[177],"speeds,":[179],"requires":[180],"50--60%":[181],"fewer":[182],"compared":[184],"utilizing":[186],"scalable":[187],"from":[190],"external":[191],"servers.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}