{"id":"https://openalex.org/W4406460908","doi":"https://doi.org/10.1109/bigdata62323.2024.10825020","title":"Custom Accessors: Enabling Scalable Data Ingestion, (Re-)Organization, and Analysis on Distributed Systems","display_name":"Custom Accessors: Enabling Scalable Data Ingestion, (Re-)Organization, and Analysis on Distributed Systems","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406460908","doi":"https://doi.org/10.1109/bigdata62323.2024.10825020"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5000893617","display_name":"Vito Giovanni Castellana","orcid":"https://orcid.org/0000-0003-3516-7903"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vito Giovanni Castellana","raw_affiliation_strings":["Pacific Northwest National Laboratory,Richland,WA,USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory,Richland,WA,USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065055260","display_name":"Burcu O. Mutlu","orcid":"https://orcid.org/0000-0001-9615-4351"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Burcu O. Mutlu","raw_affiliation_strings":["Pacific Northwest National Laboratory,Richland,WA,USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory,Richland,WA,USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051215304","display_name":"Ian Di Dio Lavore","orcid":"https://orcid.org/0009-0009-1572-3221"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ian Di Dio Lavore","raw_affiliation_strings":["Politecnico di Milano,Milano,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Milano,Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063476184","display_name":"Jesun Firoz","orcid":"https://orcid.org/0000-0002-8174-2545"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesun Firoz","raw_affiliation_strings":["Pacific Northwest National Laboratory,Richland,WA,USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory,Richland,WA,USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044344523","display_name":"Katherine Wolf","orcid":null},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Wolf","raw_affiliation_strings":["Pacific Northwest National Laboratory,Richland,WA,USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory,Richland,WA,USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074554647","display_name":"Marco Minutoli","orcid":"https://orcid.org/0000-0002-4220-1420"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Minutoli","raw_affiliation_strings":["Pacific Northwest National Laboratory,Richland,WA,USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory,Richland,WA,USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057593011","display_name":"John Feo","orcid":"https://orcid.org/0000-0001-6546-8948"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Feo","raw_affiliation_strings":["Pacific Northwest National Laboratory,Richland,WA,USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory,Richland,WA,USA","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5000893617"],"corresponding_institution_ids":["https://openalex.org/I142606810"],"apc_list":null,"apc_paid":null,"fwci":0.3755,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66511055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"189","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9997000098228455,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9997000098228455,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9951000213623047,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6931860446929932},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6345229744911194},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.44030120968818665},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32748302817344666},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2584036588668823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6931860446929932},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6345229744911194},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44030120968818665},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32748302817344666},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2584036588668823}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1285765","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1285765","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","score":0.7300000190734863,"display_name":"Zero hunger"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1963494026","https://openalex.org/W2000604789","https://openalex.org/W2155066383","https://openalex.org/W2528015584","https://openalex.org/W2846440111","https://openalex.org/W2913135575","https://openalex.org/W2963691402","https://openalex.org/W3037165769","https://openalex.org/W3082389863","https://openalex.org/W3096043505"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1982914007","https://openalex.org/W2159583675","https://openalex.org/W1824242903","https://openalex.org/W1493858311","https://openalex.org/W2155470929","https://openalex.org/W2111125783","https://openalex.org/W2394465510"],"abstract_inverted_index":{"The":[0],"emerging":[1],"class":[2],"of":[3,41,44,100,116,142,175,187,211],"high":[4,7,104],"velocity":[5],"and":[6,17,22,48,65,69,75,79,120,135,148,163,173,183,208,218],"volume":[8],"data":[9,14,50,59,216],"analytic":[10],"workflows":[11,39],"comprise":[12],"interwoven":[13],"ingestion,":[15],"organization,":[16],"processing":[18,35],"stages,":[19],"with":[20,178],"ingestion":[21,217],"organization":[23],"steps":[24,214],"often":[25],"contributing":[26,229],"comparable":[27],"or":[28],"even":[29,157],"higher":[30],"computational":[31],"costs":[32],"than":[33],"actual":[34],"steps.":[36],"Since":[37],"complex":[38],"consist":[40],"a":[42,91,103,132,140,191,222],"variety":[43,141],"phases":[45],"that":[46,111,199],"view":[47],"use":[49,181],"differently,":[51],"being":[52],"able":[53],"to":[54,73,138,159,231],"construct":[55],"efficient,":[56],"scalable,":[57],"distributed":[58,124,164,192],"structures":[60],"(arrays,":[61],"vectors,":[62],"sets,":[63],"maps,":[64],"multi-maps)":[66],"is":[67],"essential":[68],"requires":[70],"custom":[71],"methods":[72],"extend":[74],"shrink":[76],"containers,":[77],"analyze":[78],"position":[80],"data,":[81],"and,":[82],"maintain":[83],"globally-consistent":[84],"meta-data.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89],"propose":[90],"novel":[92],"data-structure":[93],"access":[94],"paradigm":[95],"based":[96],"on":[97,190],"the":[98,114,171,185,232],"concept":[99],"Accessors.":[101],"At":[102],"level,":[105],"accessors":[106],"are":[107],"customizable":[108],"callable":[109],"objects":[110],"can":[112],"modify":[113],"behavior":[115],"insert,":[117],"read,":[118],"update,":[119],"delete":[121],"operations":[122],"for":[123,204],"containers":[125],"while":[126],"preserving":[127],"atomicity":[128],"guarantees.":[129],"Accessors":[130],"provide":[131],"very":[133],"clean":[134],"natural":[136],"way":[137],"implement":[139],"programming":[143],"patterns,":[144],"e.g.,":[145],"conditional":[146],"insertion/deletion":[147],"cascading":[149],"computations,":[150],"which":[151,220],"would":[152,226],"be":[153],"otherwise":[154],"hard":[155],"(or":[156],"impossible)":[158],"express":[160],"in":[161,221],"parallel":[162],"settings":[165],"without":[166],"using":[167],"locks.":[168],"We":[169],"demonstrate":[170],"practicality":[172],"usefulness":[174],"our":[176,200],"approach":[177],"two":[179],"representative":[180],"cases":[182],"study":[184],"performance":[186],"these":[188],"applications":[189],"High-Performance":[193],"Computing":[194],"system.":[195],"Our":[196],"analysis":[197],"highlights":[198],"proposed":[201],"abstraction":[202],"allows":[203],"an":[205],"effective":[206],"overlapping":[207],"concurrent":[209],"execution":[210],"different":[212],"workflow":[213],"(e.g.,":[215],"analysis),":[219],"conventional":[223],"analytics":[224],"pipeline":[225],"execute":[227],"sequentially,":[228],"cumulatively":[230],"overall":[233],"latency.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
