{"id":"https://openalex.org/W3195673285","doi":"https://doi.org/10.1109/tbdata.2021.3106345","title":"Accelerating ML/DL Applications with Hierarchical Caching on Deduplication Storage Clusters","display_name":"Accelerating ML/DL Applications with Hierarchical Caching on Deduplication Storage Clusters","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3195673285","doi":"https://doi.org/10.1109/tbdata.2021.3106345","mag":"3195673285"},"language":"en","primary_location":{"id":"doi:10.1109/tbdata.2021.3106345","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tbdata.2021.3106345","pdf_url":"https://ieeexplore.ieee.org/ielx7/6687317/7153538/09520287.pdf","source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/6687317/7153538/09520287.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082900475","display_name":"Prince Hamandawana","orcid":"https://orcid.org/0000-0002-1030-3844"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Prince Hamandawana","raw_affiliation_strings":["Department of Computer Science and Engineering, Soongsil University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Soongsil University, Seoul, South Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085960321","display_name":"Awais Khan","orcid":"https://orcid.org/0000-0003-2603-3516"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Awais Khan","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010897170","display_name":"Jongik Kim","orcid":"https://orcid.org/0000-0002-5857-6091"},"institutions":[{"id":"https://openalex.org/I196345858","display_name":"Chungnam National University","ror":"https://ror.org/0227as991","country_code":"KR","type":"education","lineage":["https://openalex.org/I196345858"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongik Kim","raw_affiliation_strings":["Department of Artificial Intelligence, Chungnam National University, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Chungnam National University, Daejeon, South Korea","institution_ids":["https://openalex.org/I196345858"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044985062","display_name":"Tae\u2010Sun Chung","orcid":"https://orcid.org/0000-0001-5992-1136"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae-Sun Chung","raw_affiliation_strings":["Department of Artificial Intelligence, Ajou University, Suwon, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Ajou University, Suwon, South Korea","institution_ids":["https://openalex.org/I57664883"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082900475"],"corresponding_institution_ids":["https://openalex.org/I141371507"],"apc_list":null,"apc_paid":null,"fwci":0.6401,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71330789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9914000034332275,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.977400004863739,"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/data-deduplication","display_name":"Data deduplication","score":0.9790658354759216},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.844352126121521},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5089685916900635},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.450001060962677},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.42142626643180847},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3432634770870209},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2904135584831238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13784384727478027}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.9790658354759216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.844352126121521},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5089685916900635},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.450001060962677},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.42142626643180847},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3432634770870209},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2904135584831238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13784384727478027}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tbdata.2021.3106345","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tbdata.2021.3106345","pdf_url":"https://ieeexplore.ieee.org/ielx7/6687317/7153538/09520287.pdf","source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tbdata.2021.3106345","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tbdata.2021.3106345","pdf_url":"https://ieeexplore.ieee.org/ielx7/6687317/7153538/09520287.pdf","source":{"id":"https://openalex.org/S2491400915","display_name":"IEEE Transactions on Big Data","issn_l":"2332-7790","issn":["2332-7790","2372-2096"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3392754088","display_name":null,"funder_award_id":"2021-0-02051","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G6072120315","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3195673285.pdf","grobid_xml":"https://content.openalex.org/works/W3195673285.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W26020480","https://openalex.org/W120798314","https://openalex.org/W174289249","https://openalex.org/W1437397736","https://openalex.org/W1977797546","https://openalex.org/W1999984505","https://openalex.org/W2029433591","https://openalex.org/W2043409565","https://openalex.org/W2055899630","https://openalex.org/W2105557521","https://openalex.org/W2108598243","https://openalex.org/W2295166260","https://openalex.org/W2554780763","https://openalex.org/W2560209691","https://openalex.org/W2568159272","https://openalex.org/W2618530766","https://openalex.org/W2769478204","https://openalex.org/W2793900539","https://openalex.org/W2806197565","https://openalex.org/W2808357789","https://openalex.org/W2810972659","https://openalex.org/W2884794239","https://openalex.org/W2903451134","https://openalex.org/W2947635314","https://openalex.org/W2950684718","https://openalex.org/W2952925381","https://openalex.org/W2953384591","https://openalex.org/W2954729276","https://openalex.org/W2954917458","https://openalex.org/W2963108782","https://openalex.org/W2963839617","https://openalex.org/W2972863894","https://openalex.org/W2982659961","https://openalex.org/W3006437988","https://openalex.org/W3025296553","https://openalex.org/W3046819731","https://openalex.org/W3081844928","https://openalex.org/W3102408035","https://openalex.org/W3122383853","https://openalex.org/W3133301182","https://openalex.org/W4253233651","https://openalex.org/W4295312788","https://openalex.org/W6604953292","https://openalex.org/W6607057542","https://openalex.org/W6628275343","https://openalex.org/W6650418438","https://openalex.org/W6696966782","https://openalex.org/W6713134421","https://openalex.org/W6749584455","https://openalex.org/W6756668738","https://openalex.org/W6758850006","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W3144870715","https://openalex.org/W3142319788","https://openalex.org/W2587188779","https://openalex.org/W3132870970","https://openalex.org/W4385804830","https://openalex.org/W2943088381","https://openalex.org/W2074021203","https://openalex.org/W2144348063","https://openalex.org/W4296125805","https://openalex.org/W1982579475"],"abstract_inverted_index":{"Large":[0],"scale":[1],"machine":[2],"learning":[3,7],"(ML)":[4],"and":[5,25,74,150,186],"deep":[6],"(DL)":[8],"platforms":[9],"face":[10],"challenges":[11],"when":[12,88],"integrated":[13],"with":[14],"deduplication":[15,36,53,61,91,112,132,144],"enabled":[16,92],"storage":[17,27,44,69,115,145],"clusters.":[18,94,116],"In":[19,95],"the":[20,38,43,66,83,106,118,142],"quest":[21],"to":[22,50,147,177],"achieve":[23],"smart":[24],"efficient":[26],"utilization,":[28],"removal":[29],"of":[30,42,57,65,129,141,155,190],"duplicate":[31],"data":[32],"introduces":[33],"bottlenecks,":[34],"since":[35],"alters":[37],"I/O":[39],"transaction":[40],"layout":[41,146],"system.":[45],"Therefore,":[46],"it":[47],"is":[48,120],"critical":[49],"address":[51],"such":[52,71],"overhead":[54],"for":[55],"acceleration":[56,154],"ML/DL":[58,68,93,114,148,159,172],"computation":[59],"in":[60,90,113,171,188],"storage.":[62],"Existing":[63],"state":[64],"art":[67],"solutions":[70],"as":[72,175],"Alluxio":[73,185],"AutoCache":[75,187],"adopt":[76],"non":[77],"deduplication-aware":[78],"caching":[79,134],"mechanisms,":[80],"which":[81,104],"lacks":[82],"much":[84],"needed":[85],"performance":[86,107,169,192],"boost":[87],"adopted":[89],"this":[96],"paper,":[97],"we":[98],"introduce":[99],"<sc":[100,122,163],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[101,123,164],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Redup</small>":[102,124,165],",":[103],"eliminates":[105],"drop":[108,170],"caused":[109],"by":[110],"enabling":[111],"At":[117],"core,":[119],"a":[121,130,152,178],"Caching":[125],"Manager":[126],"(RDCM),":[127],"composed":[128],"2-tier":[131],"layout-aware":[133],"mechanism.":[135],"The":[136],"RDCM":[137],"provides":[138],"an":[139],"abstraction":[140],"underlying":[143],"applications":[149],"provisions":[151],"decoupled":[153],"object":[156],"reconstruction":[157],"during":[158],"read":[160],"operations.":[161],"Our":[162],"evaluation":[166],"shows":[167],"negligible":[168],"training":[173],"performances":[174],"compared":[176],"cluster":[179],"without":[180],"deduplication,":[181],"whilst":[182],"significantly":[183],"outperforming":[184],"terms":[189],"various":[191],"metrics.":[193]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
