{"id":"https://openalex.org/W4391093568","doi":"https://doi.org/10.1109/bigdata59044.2023.10386912","title":"TensorBank: Tensor Lakehouse for Foundation Model Training","display_name":"TensorBank: Tensor Lakehouse for Foundation Model Training","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391093568","doi":"https://doi.org/10.1109/bigdata59044.2023.10386912"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5061695276","display_name":"Romeo Kienzler","orcid":"https://orcid.org/0000-0002-7145-8225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romeo Kienzler","raw_affiliation_strings":["IBM Research Europe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Europe","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054744174","display_name":"Johannes Schmude","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Johannes Schmude","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039989221","display_name":"Naomi Simumba","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naomi Simumba","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042112718","display_name":"Benedikt Blumenstiel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benedikt Blumenstiel","raw_affiliation_strings":["IBM Research Europe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Europe","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004915957","display_name":"Marcus Freitag","orcid":"https://orcid.org/0009-0009-0356-7057"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcus Freitag","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047548171","display_name":"Daiki Kimura","orcid":"https://orcid.org/0000-0001-5180-1949"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daiki Kimura","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026039657","display_name":"Zolt\u00e1n Nagy","orcid":"https://orcid.org/0000-0002-5124-0368"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zoltan Arnold Nagy","raw_affiliation_strings":["IBM Research Europe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Europe","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053213491","display_name":"Michael Behrendt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Behrendt","raw_affiliation_strings":["IBM Research and Development"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research and Development","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048701479","display_name":"Hendrik F. Hamann","orcid":"https://orcid.org/0000-0001-9049-1330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hendrik Hamann","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029716503","display_name":"S. Karthik Mukkavilli","orcid":"https://orcid.org/0000-0003-4967-2644"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Karthik Mukkavilli","raw_affiliation_strings":["IBM Research Europe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Europe","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024220530","display_name":"Daniel Civitarese","orcid":"https://orcid.org/0000-0003-3335-1985"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Salles Civitarese","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72718393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3350","last_page":"3354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13650","display_name":"Computational Physics and Python Applications","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T13650","display_name":"Computational Physics and Python Applications","score":0.9991000294685364,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9825000166893005,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9746999740600586,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8518128395080566},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6312466859817505},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.5764644145965576},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5619227290153503},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5007572174072266},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4746549725532532},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4735402464866638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46940386295318604},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.45986366271972656},{"id":"https://openalex.org/keywords/geospatial-analysis","display_name":"Geospatial analysis","score":0.43856796622276306},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.39452850818634033},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2841963768005371},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.27014899253845215},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21026384830474854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8518128395080566},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6312466859817505},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.5764644145965576},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5619227290153503},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5007572174072266},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4746549725532532},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4735402464866638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46940386295318604},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.45986366271972656},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.43856796622276306},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39452850818634033},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2841963768005371},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27014899253845215},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21026384830474854},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1971959507","https://openalex.org/W1982144859","https://openalex.org/W2008085934","https://openalex.org/W2019227001","https://openalex.org/W2045125148","https://openalex.org/W2123637716","https://openalex.org/W2172259164","https://openalex.org/W2173213060","https://openalex.org/W2193503481","https://openalex.org/W2337976471","https://openalex.org/W2394680079","https://openalex.org/W2534983812","https://openalex.org/W2774761221","https://openalex.org/W2949762319","https://openalex.org/W2970119753","https://openalex.org/W2970172132","https://openalex.org/W2998731679","https://openalex.org/W3085477028","https://openalex.org/W3093789645","https://openalex.org/W3099861110","https://openalex.org/W3161850060","https://openalex.org/W3195577433","https://openalex.org/W3200026390","https://openalex.org/W4237212714","https://openalex.org/W4295312788","https://openalex.org/W4383218913","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6766978945","https://openalex.org/W6771965122","https://openalex.org/W6800751262"],"related_works":["https://openalex.org/W2376415519","https://openalex.org/W1601381279","https://openalex.org/W4294769427","https://openalex.org/W4225667838","https://openalex.org/W1895908943","https://openalex.org/W4281893144","https://openalex.org/W2374747083","https://openalex.org/W4386270999","https://openalex.org/W4399378742","https://openalex.org/W4388254351"],"abstract_inverted_index":{"Storing":[0],"and":[1,104,146,176],"streaming":[2,37],"high":[3],"dimensional":[4],"data":[5,82],"for":[6,61,155],"foundation":[7,18],"model":[8],"training":[9],"became":[10],"a":[11,30,91,97],"critical":[12],"requirement":[13],"with":[14,96],"the":[15,114],"rise":[16],"of":[17,36,113,150],"models":[19],"beyond":[20],"natural":[21],"language.":[22],"In":[23],"this":[24,161],"paper":[25],"we":[26],"introduce":[27],"TensorBank":[28],"\u2013":[29],"petabyte":[31],"scale":[32],"tensor":[33],"lakehouse":[34],"capable":[35],"tensors":[38,70],"from":[39],"Cloud":[40],"Object":[41],"Store":[42],"(COS)":[43],"to":[44,67,164],"GPU":[45,80],"memory":[46],"at":[47,132],"wire":[48],"speed":[49],"based":[50],"on":[51,71,129],"complex":[52],"relational":[53,102],"queries.":[54],"We":[55,89],"use":[56,112,149,157,166],"Hierarchical":[57],"Statistical":[58],"Indices":[59],"(HSI)":[60],"query":[62],"acceleration.":[63],"Our":[64],"architecture":[65,141,162],"allows":[66],"directly":[68],"address":[69],"block":[72],"level":[73],"using":[74,86,158],"HTTP":[75],"range":[76],"reads.":[77],"Once":[78],"in":[79],"memory,":[81],"can":[83,118],"be":[84,119],"transformed":[85],"PyTorch":[87,93],"transforms.":[88],"provide":[90],"generic":[92],"dataset":[94,99],"type":[95],"corresponding":[98],"factory":[100],"translating":[101],"queries":[103],"requested":[105],"transformations":[106],"as":[107,124],"an":[108,139],"instance.":[109],"By":[110],"making":[111,147],"HSI,":[115],"irrelevant":[116],"blocks":[117],"skipped":[120],"without":[121],"reading":[122],"them":[123],"those":[125],"indices":[126],"contain":[127],"statistics":[128],"their":[130],"content":[131],"different":[133],"hierarchical":[134],"resolution":[135],"levels.":[136],"This":[137],"is":[138],"opinionated":[140],"powered":[142],"by":[143],"open":[144],"standards":[145],"heavy":[148],"open-source":[151],"technology.":[152],"Although,":[153],"hardened":[154],"production":[156],"geospatial-temporal":[159],"data,":[160],"generalizes":[163],"other":[165],"cases":[167],"like":[168],"computer":[169],"vision,":[170],"computational":[171],"neuroscience,":[172],"biological":[173],"sequence":[174],"analysis":[175],"more.":[177]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}