{"id":"https://openalex.org/W2928790192","doi":"https://doi.org/10.14778/3364324.3364325","title":"Model slicing for supporting complex analytics with elastic inference cost and resource constraints","display_name":"Model slicing for supporting complex analytics with elastic inference cost and resource constraints","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2928790192","doi":"https://doi.org/10.14778/3364324.3364325","mag":"2928790192"},"language":"en","primary_location":{"id":"doi:10.14778/3364324.3364325","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3364324.3364325","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.01831","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001683040","display_name":"Shaofeng Cai","orcid":"https://orcid.org/0000-0001-8605-076X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Shaofeng Cai","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389329","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0003-4234-1359"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Chen","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024892041","display_name":"Beng Chin Ooi","orcid":"https://orcid.org/0000-0003-4446-1100"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Beng Chin Ooi","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000935850","display_name":"Jinyang Gao","orcid":"https://orcid.org/0000-0001-8247-1196"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyang Gao","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001683040"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.3283,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.84319026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"13","issue":"2","first_page":"86","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9958000183105469,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9850999712944031,"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/computer-science","display_name":"Computer science","score":0.7587888240814209},{"id":"https://openalex.org/keywords/slicing","display_name":"Slicing","score":0.6625935435295105},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6572651863098145},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6570279598236084},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5526248216629028},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5155155658721924},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5051882863044739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4472822844982147},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4441216289997101},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.4405301511287689},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4303112328052521},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.42806410789489746},{"id":"https://openalex.org/keywords/computational-resource","display_name":"Computational resource","score":0.4272366166114807},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4192378520965576},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3385350704193115},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.26553308963775635},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1793801486492157}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587888240814209},{"id":"https://openalex.org/C2776190703","wikidata":"https://www.wikidata.org/wiki/Q488148","display_name":"Slicing","level":2,"score":0.6625935435295105},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6572651863098145},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6570279598236084},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5526248216629028},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5155155658721924},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5051882863044739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4472822844982147},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4441216289997101},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.4405301511287689},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4303112328052521},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.42806410789489746},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.4272366166114807},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4192378520965576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3385350704193115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26553308963775635},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1793801486492157},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3364324.3364325","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3364324.3364325","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:arXiv.org:1904.01831","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.01831","pdf_url":"https://arxiv.org/pdf/1904.01831","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.01831","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.01831","pdf_url":"https://arxiv.org/pdf/1904.01831","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1591801644","https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W1836465849","https://openalex.org/W2000431947","https://openalex.org/W2062022900","https://openalex.org/W2064675550","https://openalex.org/W2090883204","https://openalex.org/W2099102906","https://openalex.org/W2108598243","https://openalex.org/W2138542364","https://openalex.org/W2150708135","https://openalex.org/W2163605009","https://openalex.org/W2167215970","https://openalex.org/W2172166488","https://openalex.org/W2194775991","https://openalex.org/W2204750386","https://openalex.org/W2279098554","https://openalex.org/W2295598076","https://openalex.org/W2302255633","https://openalex.org/W2319920447","https://openalex.org/W2331143823","https://openalex.org/W2357449897","https://openalex.org/W2401231614","https://openalex.org/W2408279554","https://openalex.org/W2421547754","https://openalex.org/W2513419314","https://openalex.org/W2514713644","https://openalex.org/W2515385951","https://openalex.org/W2531409750","https://openalex.org/W2541674938","https://openalex.org/W2547190417","https://openalex.org/W2549139847","https://openalex.org/W2551895583","https://openalex.org/W2559655401","https://openalex.org/W2593303827","https://openalex.org/W2598097916","https://openalex.org/W2604272474","https://openalex.org/W2612445135","https://openalex.org/W2612690371","https://openalex.org/W2613577383","https://openalex.org/W2622263826","https://openalex.org/W2622338386","https://openalex.org/W2624244387","https://openalex.org/W2741632195","https://openalex.org/W2752236330","https://openalex.org/W2768348081","https://openalex.org/W2795783309","https://openalex.org/W2798366733","https://openalex.org/W2905741102","https://openalex.org/W2943902758","https://openalex.org/W2949117887","https://openalex.org/W2949892913","https://openalex.org/W2950014519","https://openalex.org/W2950248853","https://openalex.org/W2951001719","https://openalex.org/W2951173410","https://openalex.org/W2952339051","https://openalex.org/W2952432176","https://openalex.org/W2962851801","https://openalex.org/W2963000224","https://openalex.org/W2963024474","https://openalex.org/W2963125010","https://openalex.org/W2963347649","https://openalex.org/W2963393494","https://openalex.org/W2963410064","https://openalex.org/W2963446712","https://openalex.org/W2963674932","https://openalex.org/W2964137095","https://openalex.org/W2964199361","https://openalex.org/W2964299589","https://openalex.org/W2964341142","https://openalex.org/W2998715488","https://openalex.org/W3046095563","https://openalex.org/W3102476541","https://openalex.org/W3118608800","https://openalex.org/W4236965008","https://openalex.org/W4250482878","https://openalex.org/W4293718192","https://openalex.org/W4297775537","https://openalex.org/W4297813615","https://openalex.org/W6685405536","https://openalex.org/W6725543821","https://openalex.org/W6725739302"],"related_works":["https://openalex.org/W2229588459","https://openalex.org/W2374430960","https://openalex.org/W2375485824","https://openalex.org/W4235807378","https://openalex.org/W120571988","https://openalex.org/W4249702239","https://openalex.org/W2742629360","https://openalex.org/W1512399864","https://openalex.org/W4389768689","https://openalex.org/W2047754121"],"abstract_inverted_index":{"Deep":[0],"learning":[1,95,126],"models":[2,16,25,127,265],"have":[3,17],"been":[4,18],"used":[5],"to":[6,20,92,128,186,204,227,253],"support":[7,93,272],"analytics":[8],"beyond":[9],"simple":[10],"aggregation,":[11],"where":[12],"deeper":[13],"and":[14,32,80,115,174,179,231],"wider":[15],"shown":[19],"yield":[21],"great":[22],"results.":[23],"These":[24],"consume":[26],"a":[27,102,113,217,237],"huge":[28],"amount":[29],"of":[30,37,52,66,71,163,166],"memory":[31],"computational":[33,44,72,134,151],"operations.":[34],"However,":[35],"most":[36],"the":[38,49,60,64,81,86,110,132,157,201,205,213,223,254,258],"large-scale":[39],"industrial":[40],"applications":[41],"are":[42],"often":[43],"budget":[45,136],"constrained.":[46],"In":[47,105],"practice,":[48],"peak":[50],"workload":[51,87,99,274],"inference":[53,277],"service":[54],"could":[55,74,140],"be":[56,75,141,243],"10x":[57],"higher":[58],"than":[59],"average":[61],"cases,":[62],"with":[63,97,112,216,239,267,275],"presence":[65],"unpredictable":[67],"extreme":[68],"cases.":[69],"Lots":[70],"resources":[73],"wasted":[76],"during":[77,235],"off-peak":[78],"hours":[79],"system":[82,89],"may":[83],"crash":[84],"when":[85],"exceeds":[88],"capacity.":[90],"How":[91],"deep":[94,125],"services":[96],"dynamic":[98],"cost-efficiently":[100],"remains":[101],"challenging":[103],"problem.":[104],"this":[106],"paper,":[107],"we":[108],"address":[109],"challenge":[111],"general":[114],"novel":[116],"training":[117],"scheme":[118],"called":[119],"model":[120,158,268],"slicing":[121,139,269],",":[122,222],"which":[123],"enables":[124],"provide":[129],"predictions":[130],"within":[131],"prescribed":[133],"resource":[135],"dynamically.":[137],"Model":[138],"viewed":[142],"as":[143],"an":[144],"elastic":[145,276],"computation":[146,249],"solution":[147],"without":[148],"requiring":[149],"more":[150],"resources.":[152],"Succinctly,":[153],"each":[154,195],"layer":[155],"in":[156,171,176,194],"is":[159,184,225,250],"divided":[160],"into":[161],"groups":[162,188,192,241],"contiguous":[164],"block":[165],"basic":[167],"components":[168],"(i.e.":[169],"neurons":[170],"dense":[172],"layers":[173],"channels":[175],"convolutional":[177],"layers),":[178],"then":[180],"partially":[181],"ordered":[182],"relation":[183],"introduced":[185],"these":[187],"by":[189,210,257],"enforcing":[190],"that":[191,264],"participated":[193],"forward":[196],"pass":[197],"always":[198],"starts":[199],"from":[200],"first":[202],"group":[203,215],"dynamically-determined":[206],"rightmost":[207,214],"group.":[208],"Trained":[209],"dynamically":[211],"indexing":[212],"single":[218],"parameter":[219],"slice":[220,259],"rate":[221],"network":[224],"engendered":[226],"build":[228],"up":[229],"group-wise":[230],"residual":[232],"representation.":[233],"Then":[234],"inference,":[236],"sub-model":[238],"fewer":[240],"can":[242,270],"readily":[244],"deployed":[245],"for":[246],"efficiency":[247],"whose":[248],"roughly":[251],"quadratic":[252],"width":[255],"controlled":[256],"rate.":[260],"Extensive":[261],"experiments":[262],"show":[263],"trained":[266],"effectively":[271],"on-demand":[273],"cost.":[278]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-04-11T00:00:00"}