{"id":"https://openalex.org/W7158215129","doi":"https://doi.org/10.1145/3805621.3807646","title":"Block-Aware Distributed Data Pipelines for Out-of-Core Tabular Machine Learning","display_name":"Block-Aware Distributed Data Pipelines for Out-of-Core Tabular Machine Learning","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7158215129","doi":"https://doi.org/10.1145/3805621.3807646"},"language":null,"primary_location":{"id":"doi:10.1145/3805621.3807646","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805621.3807646","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth European Workshop on Machine Learning and Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805621.3807646","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120325217","display_name":"Dimitris Metaxakis","orcid":null},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]},{"id":"https://openalex.org/I4210135709","display_name":"Industrial Systems Institute","ror":"https://ror.org/02sy6k521","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210135709"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Dimitris Metaxakis","raw_affiliation_strings":["Department of Computer Engineering and Informatics, University of Patras, Patras, Greece and Archimedes Unit, Athena Research Center, Athens, Greece"],"raw_orcid":"https://orcid.org/0009-0005-4452-891X","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering and Informatics, University of Patras, Patras, Greece and Archimedes Unit, Athena Research Center, Athens, Greece","institution_ids":["https://openalex.org/I4210135709","https://openalex.org/I174878644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120325216","display_name":"Argiris Sofotasios","orcid":null},"institutions":[{"id":"https://openalex.org/I174878644","display_name":"University of Patras","ror":"https://ror.org/017wvtq80","country_code":"GR","type":"education","lineage":["https://openalex.org/I174878644"]},{"id":"https://openalex.org/I4210135709","display_name":"Industrial Systems Institute","ror":"https://ror.org/02sy6k521","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210135709"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Argiris Sofotasios","raw_affiliation_strings":["Department of Computer Engineering and Informatics, University of Patras, Patras, Greece and Archimedes Unit, Athena Research Center, Athens, Greece"],"raw_orcid":"https://orcid.org/0009-0002-5282-8064","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering and Informatics, University of Patras, Patras, Greece and Archimedes Unit, Athena Research Center, Athens, Greece","institution_ids":["https://openalex.org/I4210135709","https://openalex.org/I174878644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009967164","display_name":"Chrysostomos Stylios","orcid":"https://orcid.org/0000-0002-2888-6515"},"institutions":[{"id":"https://openalex.org/I4210135709","display_name":"Industrial Systems Institute","ror":"https://ror.org/02sy6k521","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210135709"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Chrysostomos Stylios","raw_affiliation_strings":["Industrial Systems Institute, Athena Research Center, Patras, Greece and Department of Informatics and Telecommunications, University of Ioannina, Arta, Greece"],"raw_orcid":"https://orcid.org/0000-0002-2888-6515","affiliations":[{"raw_affiliation_string":"Industrial Systems Institute, Athena Research Center, Patras, Greece and Department of Informatics and Telecommunications, University of Ioannina, Arta, Greece","institution_ids":["https://openalex.org/I4210135709"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133651591","display_name":"Panagiotis Hadjidoukas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135709","display_name":"Industrial Systems Institute","ror":"https://ror.org/02sy6k521","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210135709"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Panagiotis Hadjidoukas","raw_affiliation_strings":["Department of Computer Engineering and Informatics, University of Patras, Patras, Greece and Industrial Systems Institute, Athena Research Center, Patras, Greece"],"raw_orcid":"https://orcid.org/0000-0002-2528-7568","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering and Informatics, University of Patras, Patras, Greece and Industrial Systems Institute, Athena Research Center, Patras, Greece","institution_ids":["https://openalex.org/I4210135709"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5120325217"],"corresponding_institution_ids":["https://openalex.org/I174878644","https://openalex.org/I4210135709"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94747754,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"346","last_page":"354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.21040000021457672,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.21040000021457672,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.1941000074148178,"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/T14347","display_name":"Big Data and Digital Economy","score":0.15710000693798065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6653000116348267},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5638999938964844},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.49480000138282776},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.48669999837875366},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.474700003862381},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4514000117778778},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.42879998683929443},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.3955000042915344},{"id":"https://openalex.org/keywords/simultaneous-multithreading","display_name":"Simultaneous multithreading","score":0.3718999922275543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8181999921798706},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6653000116348267},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5638999938964844},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.49480000138282776},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.474700003862381},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.42879998683929443},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4115999937057495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4104999899864197},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40470001101493835},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.388700008392334},{"id":"https://openalex.org/C85717602","wikidata":"https://www.wikidata.org/wiki/Q82178","display_name":"Simultaneous multithreading","level":4,"score":0.3718999922275543},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3596000075340271},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.34470000863075256},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C13926793","wikidata":"https://www.wikidata.org/wiki/Q3507155","display_name":"Group method of data handling","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C105122174","wikidata":"https://www.wikidata.org/wiki/Q322202","display_name":"Garbage collection","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805621.3807646","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805621.3807646","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth European Workshop on Machine Learning and Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805621.3807646","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805621.3807646","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixth European Workshop on Machine Learning and Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2963979055","https://openalex.org/W3012125688","https://openalex.org/W3027784805","https://openalex.org/W3086105743","https://openalex.org/W3138303811","https://openalex.org/W3169404295","https://openalex.org/W3196732841","https://openalex.org/W4214634229","https://openalex.org/W4312131336","https://openalex.org/W4390906233","https://openalex.org/W4394944658","https://openalex.org/W4394945038","https://openalex.org/W4408060982","https://openalex.org/W4412474694","https://openalex.org/W4416068844","https://openalex.org/W7155557975"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"Machine":[1],"Learning":[2],"(ML)":[3],"pipelines":[4],"are":[5],"often":[6],"bottle-necked":[7],"by":[8,92,119],"prolonged":[9],"data":[10,17,29,52,121],"stalls,":[11],"particularly":[12],"in":[13,36,180],"out-of-core":[14,56],"settings":[15],"where":[16],"volumes":[18],"exceed":[19],"main":[20],"memory":[21,147],"capacity.":[22],"In":[23,44],"such":[24],"cases,":[25],"preprocessing":[26,69,88,131],"and":[27,95,129,157,168],"batch-wise":[28],"loading":[30],"impose":[31],"substantial":[32],"I/O":[33,94,117,148],"overhead,":[34],"resulting":[35],"underutilization":[37],"of":[38,60,100],"accelerators":[39],"and,":[40],"consequently,":[41],"limited":[42],"scalability.":[43],"this":[45],"work,":[46],"we":[47],"present":[48],"a":[49,111,124,175],"block-aware":[50],"distributed":[51,72],"pipeline":[53],"system":[54,142],"for":[55],"tabular":[57,177],"ML":[58],"composed":[59],"two":[61],"complementary":[62],"components.":[63],"The":[64,108],"first":[65],"extends":[66],"the":[67,87,103,134,140,152],"Mneme":[68],"framework":[70],"to":[71,155,163],"environments":[73],"through":[74],"an":[75],"MPI-based,":[76],"multi-level":[77],"parallel":[78],"execution":[79],"model.":[80],"Python":[81],"multithreading":[82],"is":[83,90,110],"also":[84],"employed,":[85],"as":[86],"workload":[89],"dominated":[91],"disk":[93],"native":[96],"backend":[97],"execution,":[98],"both":[99],"which":[101],"release":[102],"Global":[104],"Interpreter":[105],"Lock":[106],"(GIL).":[107],"second":[109],"cache-aware":[112],"PyTorch":[113],"DataLoader":[114],"that":[115,139],"reduces":[116],"operations":[118],"retrieving":[120],"batches":[122],"from":[123,150],"dedicated":[125],"application-level":[126],"in-memory":[127],"cache":[128],"applying":[130],"operators":[132],"on":[133,174],"fly.":[135],"Experimental":[136],"results":[137],"show":[138],"proposed":[141],"enforces":[143],"block-level":[144],"locality,":[145],"reducing":[146],"amplification":[149],"44.9\u00d7":[151],"dataset":[153,178],"size":[154],"3.7\u00d7,":[156],"translates":[158],"these":[159],"reductions":[160],"into":[161],"up":[162],"9.3\u00d7":[164],"higher":[165],"data-loading":[166],"throughput":[167],"significant":[169],"end-to-end":[170],"training":[171],"time":[172],"savings":[173],"large-scale":[176],"stored":[179],"raw-text":[181],"CSV":[182],"format.":[183]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-04-30T00:00:00"}