{"id":"https://openalex.org/W4399208454","doi":"https://doi.org/10.14778/3659437.3659456","title":"Everything You Always Wanted to Know About Storage Compressibility of Pre-Trained ML Models but Were Afraid to Ask","display_name":"Everything You Always Wanted to Know About Storage Compressibility of Pre-Trained ML Models but Were Afraid to Ask","publication_year":2024,"publication_date":"2024-04-01","ids":{"openalex":"https://openalex.org/W4399208454","doi":"https://doi.org/10.14778/3659437.3659456"},"language":"en","primary_location":{"id":"doi:10.14778/3659437.3659456","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3659437.3659456","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009653872","display_name":"Zhaoyuan Su","orcid":"https://orcid.org/0000-0002-5647-8439"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhaoyuan Su","raw_affiliation_strings":["University of Virginia"],"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635222","display_name":"Ammar Ahmed","orcid":"https://orcid.org/0000-0002-1361-3442"},"institutions":[{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ammar Ahmed","raw_affiliation_strings":["University of Minnesota"],"affiliations":[{"raw_affiliation_string":"University of Minnesota","institution_ids":["https://openalex.org/I2800403580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687845","display_name":"Zirui Wang","orcid":"https://orcid.org/0000-0002-5927-6322"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zirui Wang","raw_affiliation_strings":["University of Virginia"],"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054645319","display_name":"Ali Anwar","orcid":"https://orcid.org/0000-0003-4487-2436"},"institutions":[{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Anwar","raw_affiliation_strings":["University of Minnesota"],"affiliations":[{"raw_affiliation_string":"University of Minnesota","institution_ids":["https://openalex.org/I2800403580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079187166","display_name":"Yue Cheng","orcid":"https://orcid.org/0000-0003-1695-4864"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Cheng","raw_affiliation_strings":["University of Virginia"],"affiliations":[{"raw_affiliation_string":"University of Virginia","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009653872"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":0.3663,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57200419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"17","issue":"8","first_page":"2036","last_page":"2049"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9972000122070312,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9839000105857849,"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/lossy-compression","display_name":"Lossy compression","score":0.8202985525131226},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6766941547393799},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6634219884872437},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5747870802879333},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5393706560134888},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.5377109050750732},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5089359283447266},{"id":"https://openalex.org/keywords/data-reduction","display_name":"Data reduction","score":0.4767766296863556},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4384308457374573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31962865591049194},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18962660431861877}],"concepts":[{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.8202985525131226},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6766941547393799},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6634219884872437},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5747870802879333},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5393706560134888},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.5377109050750732},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5089359283447266},{"id":"https://openalex.org/C153914771","wikidata":"https://www.wikidata.org/wiki/Q5227343","display_name":"Data reduction","level":2,"score":0.4767766296863556},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4384308457374573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31962865591049194},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18962660431861877},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3659437.3659456","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3659437.3659456","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2002934700","https://openalex.org/W2022126655","https://openalex.org/W2107745473","https://openalex.org/W2132069633","https://openalex.org/W2134792144","https://openalex.org/W2164030956","https://openalex.org/W2168694323","https://openalex.org/W2276892413","https://openalex.org/W2294581520","https://openalex.org/W2475932436","https://openalex.org/W2525726844","https://openalex.org/W2606429533","https://openalex.org/W2612457169","https://openalex.org/W2734941459","https://openalex.org/W2886377182","https://openalex.org/W2912122742","https://openalex.org/W2912174957","https://openalex.org/W2912500072","https://openalex.org/W2914304175","https://openalex.org/W2959531572","https://openalex.org/W2962761403","https://openalex.org/W3037979316","https://openalex.org/W3098592065","https://openalex.org/W3100985894","https://openalex.org/W3118404249","https://openalex.org/W3132597740","https://openalex.org/W3174738244","https://openalex.org/W3184606595","https://openalex.org/W3198189630","https://openalex.org/W3202442802","https://openalex.org/W3203587904","https://openalex.org/W4283394632","https://openalex.org/W4312429406","https://openalex.org/W4320061060","https://openalex.org/W4376599704","https://openalex.org/W6770056184"],"related_works":["https://openalex.org/W2385628723","https://openalex.org/W2547124190","https://openalex.org/W3180760233","https://openalex.org/W3035703949","https://openalex.org/W4247601675","https://openalex.org/W1970394887","https://openalex.org/W755971114","https://openalex.org/W2118338613","https://openalex.org/W1982468865","https://openalex.org/W4313046148"],"abstract_inverted_index":{"As":[0],"the":[1,43,61,175,180,209,249],"number":[2],"of":[3,40,42,47,67,78,179,229],"pre-trained":[4,28],"machine":[5],"learning":[6],"(ML)":[7],"models":[8],"is":[9,34,131,232],"growing":[10],"exponentially,":[11],"data":[12,20,54,79,86,88,101,120,144,204],"reduction":[13,21,55,80,121,205],"tools":[14,122],"are":[15,23,123],"not":[16,24,124],"catching":[17],"up.":[18],"Existing":[19],"techniques":[22,98],"specifically":[25],"designed":[26],"for":[27,135,146],"model":[29,105,107,110,251,256],"(PTM)":[30],"dataset":[31],"files.":[32],"This":[33,58],"largely":[35],"due":[36],"to":[37,53,65,91,109,187,213],"a":[38,132,157,172,194,239],"lack":[39],"understanding":[41],"patterns":[44],"and":[45,56,81,235,248],"characteristics":[46,145],"these":[48,97],"datasets,":[49],"especially":[50],"those":[51],"relevant":[52],"compressibility.":[57,72],"paper":[59],"presents":[60],"first,":[62],"exhaustive":[63],"analysis":[64,74,95],"date":[66],"PTM":[68,128],"datasets":[69],"on":[70],"storage":[71,148,189],"Our":[73,94],"spans":[75],"different":[76,218],"types":[77],"compression":[82,137,164,195,227],"techniques,":[83],"from":[84,104],"hash-based":[85],"deduplication,":[87],"similarity":[89],"detection,":[90],"dictionary-coding":[92],"compression.":[93],"explores":[96],"at":[99],"three":[100],"granularity":[102],"levels,":[103],"layers,":[106],"chunks,":[108],"parameters.":[111],"We":[112,191],"draw":[113],"new":[114,136],"observations":[115],"that":[116,118,139,174,197,216,222],"indicate":[117],"modern":[119],"effective":[125,147,211],"when":[126],"handling":[127],"datasets.":[129],"There":[130],"pressing":[133],"need":[134],"methods":[138],"take":[140],"into":[141],"account":[142],"PTMs'":[143],"reduction.":[149],"Motivated":[150],"by":[151],"our":[152],"findings,":[153],"we":[154],"design":[155],"Elf,":[156],"simple":[158],"yet":[159],"effective,":[160],"error-bounded,":[161],"lossy":[162,245],"floating-point":[163,168],"method.":[165],"Elf":[166,199],"transforms":[167],"parameters":[169,182],"in":[170],"such":[171],"way":[173],"common":[176],"exponent":[177],"field":[178],"transformed":[181],"can":[183],"be":[184],"completely":[185],"eliminated":[186],"save":[188],"space.":[190],"develop":[192],"Elves,":[193],"framework":[196],"integrates":[198],"along":[200],"with":[201,254],"several":[202],"other":[203],"methods.":[206],"Elves":[207,223],"uses":[208],"most":[210],"method":[212],"compress":[214],"PTMs":[215],"exhibit":[217],"patterns.":[219],"Evaluation":[220],"shows":[221],"achieves":[224],"an":[225,243],"overall":[226],"ratio":[228],"1.52\u00d7,":[230],"which":[231],"1.31\u00d7,":[233],"1.32\u00d7":[234],"1.29\u00d7":[236],"higher":[237],"than":[238],"general-purpose":[240],"compressor":[241,246],"(zstd),":[242],"error-bounded":[244],"(SZ3),":[247],"uniform":[250],"quantization,":[252],"respectively,":[253],"negligible":[255],"accuracy":[257],"loss.":[258]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}