{"id":"https://openalex.org/W4408125694","doi":"https://doi.org/10.1109/access.2025.3547623","title":"Accelerating Distributed Repartition Joins on Skewed Datasets via Patch-Based Shuffling","display_name":"Accelerating Distributed Repartition Joins on Skewed Datasets via Patch-Based Shuffling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408125694","doi":"https://doi.org/10.1109/access.2025.3547623"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3547623","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3547623","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3547623","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032810499","display_name":"Evdokia Kassela","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Evdokia Kassela","raw_affiliation_strings":["School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece","National Technical University of Athens, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004421134","display_name":"Ioannis Konstantinou","orcid":"https://orcid.org/0000-0002-7142-8106"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ioannis Konstantinou","raw_affiliation_strings":["Department of Informatics and Telecommunications, University of Thessaly, Lamia, Greece","University of Thessaly, Lamia, Greece"],"raw_orcid":"https://orcid.org/0000-0002-7142-8106","affiliations":[{"raw_affiliation_string":"Department of Informatics and Telecommunications, University of Thessaly, Lamia, Greece","institution_ids":["https://openalex.org/I145722265"]},{"raw_affiliation_string":"University of Thessaly, Lamia, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023526161","display_name":"Nectarios Koziris","orcid":"https://orcid.org/0000-0002-4890-8427"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nectarios Koziris","raw_affiliation_strings":["School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece","National Technical University of Athens, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"National Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04337848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"41068","last_page":"41096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.45669999718666077,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.45669999718666077,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.42590001225471497,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.41130000352859497,"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/shuffling","display_name":"Shuffling","score":0.8642759323120117},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.8235172629356384},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7554081678390503},{"id":"https://openalex.org/keywords/repartition","display_name":"Repartition","score":0.464769184589386},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3918006122112274},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1556093990802765}],"concepts":[{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.8642759323120117},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.8235172629356384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554081678390503},{"id":"https://openalex.org/C2780066083","wikidata":"https://www.wikidata.org/wiki/Q4191004","display_name":"Repartition","level":2,"score":0.464769184589386},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3918006122112274},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1556093990802765},{"id":"https://openalex.org/C15708023","wikidata":"https://www.wikidata.org/wiki/Q80083","display_name":"Humanities","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3547623","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3547623","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a233cb1eaccf40e89abbd5c99457b87a","is_oa":true,"landing_page_url":"https://doaj.org/article/a233cb1eaccf40e89abbd5c99457b87a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 41068-41096 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3547623","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3547623","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1992101337","https://openalex.org/W2011129635","https://openalex.org/W2032392871","https://openalex.org/W2037027334","https://openalex.org/W2043099794","https://openalex.org/W2072541977","https://openalex.org/W2105947650","https://openalex.org/W2110086534","https://openalex.org/W2125529470","https://openalex.org/W2126483728","https://openalex.org/W2140509629","https://openalex.org/W2173213060","https://openalex.org/W2277471751","https://openalex.org/W2350175208","https://openalex.org/W2406955896","https://openalex.org/W2430301697","https://openalex.org/W2435648513","https://openalex.org/W2542459869","https://openalex.org/W2559513690","https://openalex.org/W2577702044","https://openalex.org/W2731949733","https://openalex.org/W2799137389","https://openalex.org/W2921130045","https://openalex.org/W2945526390","https://openalex.org/W2981805472","https://openalex.org/W3032604551","https://openalex.org/W3037843194","https://openalex.org/W3119448165","https://openalex.org/W3140576235","https://openalex.org/W3166319166","https://openalex.org/W3197515312","https://openalex.org/W3202743957","https://openalex.org/W4281782335","https://openalex.org/W4285503945","https://openalex.org/W4322576553","https://openalex.org/W4367358006","https://openalex.org/W4377079727","https://openalex.org/W4379382508","https://openalex.org/W4381785594","https://openalex.org/W4386280834","https://openalex.org/W4388973257","https://openalex.org/W4389495243","https://openalex.org/W4389990267","https://openalex.org/W4400134761","https://openalex.org/W6600634475","https://openalex.org/W6635650928","https://openalex.org/W6684084819","https://openalex.org/W6927418314"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4213239787","https://openalex.org/W2045745654","https://openalex.org/W2114337652","https://openalex.org/W4377131110","https://openalex.org/W4388857216","https://openalex.org/W4294559962","https://openalex.org/W2046590706"],"abstract_inverted_index":{"In":[0],"distributed":[1,37,103,255],"workloads":[2,194],"involving":[3],"joins":[4,207],"and":[5,18,43,74,81,98,125,141,146,169,181,195,232,243],"aggregations,":[6],"skewed":[7,247],"attribute":[8],"values":[9],"often":[10,24],"cause":[11],"load":[12,58,126,136,180],"balancing":[13,137],"issues,":[14],"leading":[15],"to":[16,36,77,133,201,204,210,225],"stragglers":[17],"increased":[19],"execution":[20,38,104,197],"times.":[21],"Existing":[22],"solutions":[23],"rely":[25],"on":[26,177],"cost-based":[27],"models,":[28],"require":[29],"extensive":[30],"parameter":[31,96],"tuning,":[32,97],"or":[33],"necessitate":[34],"modifications":[35],"engines,":[39],"limiting":[40],"their":[41],"usability":[42],"generality.":[44],"To":[45],"address":[46],"this":[47],"challenge,":[48],"we":[49],"present":[50],"a":[51,107,241],"novel":[52],"patch-based":[53,130],"repartitioning":[54],"algorithm":[55],"that":[56,188],"eliminates":[57],"imbalances":[59],"while":[60,158,213],"minimizing":[61],"network":[62,160,182],"overhead.":[63],"Our":[64,238],"approach":[65],"extends":[66],"the":[67,111,165,233,252],"subset-replicate":[68],"technique":[69,91],"by":[70,199],"leveraging":[71],"data":[72,79,84,144,183,227,248,256],"distribution":[73,155],"location":[75],"statistics":[76,123],"optimize":[78],"locality":[80],"reduce":[82],"unnecessary":[83],"movement.":[85,184],"Unlike":[86],"traditional":[87],"hash-based":[88,206],"methods,":[89],"our":[90,173,189],"is":[92],"skew-insensitive,":[93],"requires":[94],"no":[95],"integrates":[99],"seamlessly":[100],"into":[101],"existing":[102],"engines":[105],"as":[106],"drop-in":[108],"replacement":[109],"for":[110,246],"shuffle":[112],"mechanism.":[113],"The":[114],"proposed":[115],"method":[116,190],"operates":[117],"in":[118],"three":[119],"distinct":[120],"stages:":[121],"(1)":[122],"collection":[124],"threshold":[127],"computation,":[128],"(2)":[129],"subgroup":[131],"assignment":[132],"ensure":[134],"optimal":[135],"with":[138],"minimal":[139],"replication,":[140],"(3)":[142],"informed":[143],"shuffling":[145],"join":[147],"execution.":[148],"This":[149],"structured":[150],"process":[151],"ensures":[152],"even":[153],"workload":[154],"across":[156],"workers":[157],"reducing":[159],"I/O.":[161],"Theoretical":[162],"analysis":[163],"proves":[164],"scalability,":[166],"skew":[167,219],"robustness,":[168],"load-balancing":[170],"guarantees":[171],"of":[172,254],"approach,":[174],"establishing":[175],"bounds":[176],"maximum":[178],"worker":[179,230],"Experimental":[185],"evaluations":[186],"demonstrate":[187],"achieves":[191],"perfectly":[192],"balanced":[193],"reduces":[196],"time":[198],"up":[200],"81%":[202],"compared":[203],"conventional":[205],"under":[208],"moderate":[209],"high":[211],"skew,":[212],"introducing":[214],"negligible":[215],"overhead":[216],"at":[217],"low":[218],"levels.":[220],"These":[221],"improvements":[222],"are":[223],"attributed":[224],"reduced":[226],"movement,":[228],"optimized":[229],"utilization,":[231],"algorithm\u2019s":[234],"robust":[235],"theoretical":[236],"foundation.":[237],"research":[239],"provides":[240],"versatile":[242],"practical":[244],"solution":[245],"processing,":[249],"significantly":[250],"advancing":[251],"efficiency":[253],"management":[257],"systems.":[258]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}