{"id":"https://openalex.org/W4396601589","doi":"https://doi.org/10.14778/3648160.3648182","title":"MetaStore: Analyzing Deep Learning Meta-Data at Scale","display_name":"MetaStore: Analyzing Deep Learning Meta-Data at Scale","publication_year":2024,"publication_date":"2024-02-01","ids":{"openalex":"https://openalex.org/W4396601589","doi":"https://doi.org/10.14778/3648160.3648182"},"language":"en","primary_location":{"id":"doi:10.14778/3648160.3648182","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3648160.3648182","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.arizona.edu/bitstream/10150/672406/1/3648160.3648182.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035400091","display_name":"Huayi Zhang","orcid":"https://orcid.org/0009-0008-8547-2483"},"institutions":[{"id":"https://openalex.org/I4210106031","display_name":"Technical Products Incorporation (United States)","ror":"https://ror.org/01f0gap96","country_code":"US","type":"company","lineage":["https://openalex.org/I4210106031"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Huayi Zhang","raw_affiliation_strings":["WPI, Data Science, Worcester, MA"],"affiliations":[{"raw_affiliation_string":"WPI, Data Science, Worcester, MA","institution_ids":["https://openalex.org/I4210106031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104344595","display_name":"Binwei Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Binwei Yan","raw_affiliation_strings":["MIT, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"MIT, Cambridge, MA","institution_ids":["https://openalex.org/I4210110987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049926126","display_name":"Lei Cao","orcid":"https://orcid.org/0000-0001-9909-8607"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]},{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Cao","raw_affiliation_strings":["U of Arizona, CS; MIT, CSAIL, Cambridge, MA","U of Arizona, CS"],"affiliations":[{"raw_affiliation_string":"U of Arizona, CS; MIT, CSAIL, Cambridge, MA","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"U of Arizona, CS","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Madden","raw_affiliation_strings":["MIT, CSAIL, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"MIT, CSAIL, Cambridge, MA","institution_ids":["https://openalex.org/I4210110987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008269094","display_name":"Elke A. Rundensteiner","orcid":"https://orcid.org/0000-0001-5375-9254"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elke Rundensteiner","raw_affiliation_strings":["WPI, Computer Science, Worcester, MA"],"affiliations":[{"raw_affiliation_string":"WPI, Computer Science, Worcester, MA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035400091"],"corresponding_institution_ids":["https://openalex.org/I4210106031"],"apc_list":null,"apc_paid":null,"fwci":1.7034,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85947865,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"17","issue":"6","first_page":"1446","last_page":"1459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9975000023841858,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9975000023841858,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9919999837875366,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9918000102043152,"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/scale","display_name":"Scale (ratio)","score":0.5580503940582275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5325262546539307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4825391173362732},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3362271785736084},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.12005764245986938},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10793498158454895}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5580503940582275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5325262546539307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4825391173362732},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3362271785736084},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.12005764245986938},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10793498158454895}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3648160.3648182","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3648160.3648182","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:repository.arizona.edu:10150/672406","is_oa":true,"landing_page_url":"http://hdl.handle.net/10150/672406","pdf_url":"https://repository.arizona.edu/bitstream/10150/672406/1/3648160.3648182.pdf","source":{"id":"https://openalex.org/S4306400271","display_name":"UA Campus Repository (The University of Arizona)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138006243","host_organization_name":"University of Arizona","host_organization_lineage":["https://openalex.org/I138006243"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"1459","raw_type":"Proceedings"}],"best_oa_location":{"id":"pmh:oai:repository.arizona.edu:10150/672406","is_oa":true,"landing_page_url":"http://hdl.handle.net/10150/672406","pdf_url":"https://repository.arizona.edu/bitstream/10150/672406/1/3648160.3648182.pdf","source":{"id":"https://openalex.org/S4306400271","display_name":"UA Campus Repository (The University of Arizona)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138006243","host_organization_name":"University of Arizona","host_organization_lineage":["https://openalex.org/I138006243"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"1459","raw_type":"Proceedings"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1704297680","display_name":"An Automated High-Content Imaging Platform for Caenorhabditis elegans","funder_award_id":"2327954","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2848276175","display_name":null,"funder_award_id":"NRT-HDR-2021871","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4639191150","display_name":"III:Small: Outlier Discovery Paradigm","funder_award_id":"1910880","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5436171597","display_name":null,"funder_award_id":"1815866","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5682276318","display_name":"Collaborative Research: Elements: A Self-tuning Anomaly Detection Service","funder_award_id":"2103799","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5945190869","display_name":"Collaborative Research: ELEMENTS: Tuning-free Anomaly Detection Service","funder_award_id":"2103832","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6249850884","display_name":"REU SITE: DATA SCIENCE RESEARCH FOR HEALTHY COMMUNITIES IN THE DIGITAL AGE","funder_award_id":"1852498","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396601589.pdf","grobid_xml":"https://content.openalex.org/works/W4396601589.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W2136848157","https://openalex.org/W2137406659","https://openalex.org/W2170240176","https://openalex.org/W2194775991","https://openalex.org/W2206858481","https://openalex.org/W2340222647","https://openalex.org/W2440722286","https://openalex.org/W2473418344","https://openalex.org/W2584502673","https://openalex.org/W2617766261","https://openalex.org/W2769644379","https://openalex.org/W2775776326","https://openalex.org/W2798535736","https://openalex.org/W2805997383","https://openalex.org/W2896457183","https://openalex.org/W2921189944","https://openalex.org/W2922064308","https://openalex.org/W2939984132","https://openalex.org/W2946900926","https://openalex.org/W2948092338","https://openalex.org/W2962858109","https://openalex.org/W2963693747","https://openalex.org/W3004146535","https://openalex.org/W3014791201","https://openalex.org/W3015640161","https://openalex.org/W3101656801","https://openalex.org/W3166159471","https://openalex.org/W3168479843","https://openalex.org/W3174931113","https://openalex.org/W3196353935","https://openalex.org/W3196684075","https://openalex.org/W4205750058","https://openalex.org/W4214502238","https://openalex.org/W4238057246","https://openalex.org/W4287116371","https://openalex.org/W4301183982","https://openalex.org/W4312918339","https://openalex.org/W4380433201","https://openalex.org/W4389609577","https://openalex.org/W4391097721","https://openalex.org/W6687483927","https://openalex.org/W6750523955","https://openalex.org/W6767887823","https://openalex.org/W6785828342","https://openalex.org/W6790310347","https://openalex.org/W6798544130","https://openalex.org/W7001767000"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W4395014643","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"The":[0],"process":[1],"of":[2,11,43,85,87,97,112,155,189,221],"training":[3],"deep":[4,247],"learning":[5,248],"models":[6,249],"produces":[7],"a":[8,78,186],"huge":[9],"amount":[10],"meta-data,":[12],"including":[13],"but":[14],"not":[15],"limited":[16],"to":[17,30,39,64,69,104,123,175,196,210,271,279],"losses,":[18],"hidden":[19],"feature":[20,34],"embeddings,":[21],"and":[22,33,59,72,108,146,161,180,215,234,241,254,256,259,276],"gradients.":[23],"Model":[24],"diagnosis":[25],"tools":[26],"have":[27,62],"been":[28],"developed":[29],"analyze":[31,109,197],"losses":[32],"embeddings":[35],"with":[36],"the":[37,41,83,88,95,139,144,152,156,169,177,194,198,212,231],"aim":[38],"improve":[40],"performance":[42],"these":[44,115,228],"models.":[45,116],"However,":[46],"gradients,":[47,148,171],"despite":[48],"carrying":[49],"rich":[50,187],"information":[51],"that":[52,131,192,263],"is":[53,149],"potentially":[54],"relevant":[55],"for":[56,151,200],"model":[57,204],"interpretation":[58],"data":[60,201],"debugging,":[61],"yet":[63],"be":[65],"fully":[66],"explored":[67],"due":[68],"their":[70],"size":[71,79],"complexity.":[73],"Each":[74],"single":[75],"gradient":[76,178],"has":[77],"as":[80,82,251],"large":[81,110],"number":[84],"parameters":[86],"neural":[89],"net":[90],"-":[91],"often":[92],"measured":[93],"in":[94,114,138,273,281],"tens":[96],"millions.":[98],"This":[99],"makes":[100],"it":[101],"extremely":[102],"challenging":[103],"efficiently":[105],"collect,":[106],"store,":[107],"numbers":[111],"gradients":[113,163,199,214],"In":[117],"this":[118,125,222],"work,":[119],"we":[120],"develop":[121],"MetaStore":[122,127,184,225,264],"fill":[124],"gap.":[126],"leverages":[128],"our":[129],"observation":[130],"storing":[132],"certain":[133],"compact":[134,167,232],"intermediate":[135],"results":[136],"produced":[137],"back":[140],"propagation":[141],"process,":[142],"namely,":[143],"prefix":[145,160,233],"suffix":[147,162,235],"sufficient":[150],"exact":[153],"restoration":[154],"original":[157,170,213],"gradient.":[158],"These":[159],"are":[164],"much":[165],"more":[166],"than":[168,207],"thus":[172],"allowing":[173],"us":[174],"address":[176],"collection":[179],"storage":[181,274],"challenges.":[182],"Furthermore,":[183],"features":[185],"set":[188],"analytics":[190,218,239],"operators":[191,229],"allow":[193],"users":[195],"debugging":[202],"or":[203],"interpretation.":[205],"Rather":[206],"first":[208],"having":[209],"restore":[211],"then":[216],"run":[217],"on":[219,230,245],"top":[220],"decompressed":[223],"view,":[224],"directly":[226],"executes":[227],"structures,":[236],"making":[237],"gradient-based":[238],"efficient":[240],"scalable.":[242],"Our":[243],"experiments":[244],"popular":[246],"such":[250],"VGG,":[252],"BERT,":[253],"ResNet":[255],"benchmark":[257],"image":[258],"text":[260],"datasets":[261],"demonstrate":[262],"outperforms":[265],"strong":[266],"baseline":[267],"methods":[268],"from":[269,277],"4":[270],"678x":[272],"costs":[275],"2":[278],"1000x":[280],"running":[282],"time.":[283]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}