{"id":"https://openalex.org/W4206764514","doi":"https://doi.org/10.1109/bigdata52589.2021.9671376","title":"FASCA: Framework for Automatic Scalable Acceleration of ML Pipeline","display_name":"FASCA: Framework for Automatic Scalable Acceleration of ML Pipeline","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4206764514","doi":"https://doi.org/10.1109/bigdata52589.2021.9671376"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata52589.2021.9671376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671376","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","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/A5101566703","display_name":"Mayank Mishra","orcid":"https://orcid.org/0000-0003-2047-3457"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Mayank Mishra","raw_affiliation_strings":["TCS Research, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, Mumbai, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043317053","display_name":"Archisman Bhowmick","orcid":"https://orcid.org/0009-0002-8855-7841"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Archisman Bhowmick","raw_affiliation_strings":["TCS Research, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, Mumbai, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086400313","display_name":"Rekha Singhal","orcid":"https://orcid.org/0000-0002-3712-1784"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rekha Singhal","raw_affiliation_strings":["TCS Research, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, Mumbai, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101566703"],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":0.3109,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47169811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1867","last_page":"1876"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9948999881744385,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9948999881744385,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9904000163078308,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.988099992275238,"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/bottleneck","display_name":"Bottleneck","score":0.8345053195953369},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8103166818618774},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.7147958278656006},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6939971446990967},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6342986822128296},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5657322406768799},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4058653712272644},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2814601957798004},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2273922860622406},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2048180103302002},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10303616523742676}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8345053195953369},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8103166818618774},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.7147958278656006},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6939971446990967},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6342986822128296},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5657322406768799},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4058653712272644},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2814601957798004},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2273922860622406},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2048180103302002},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10303616523742676},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata52589.2021.9671376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata52589.2021.9671376","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2104266030","https://openalex.org/W2189162242","https://openalex.org/W2245493112","https://openalex.org/W2520985585","https://openalex.org/W2776147949","https://openalex.org/W2908654642","https://openalex.org/W2981859891","https://openalex.org/W3043050134","https://openalex.org/W3097265026","https://openalex.org/W3198045395","https://openalex.org/W4287365853","https://openalex.org/W4287761514","https://openalex.org/W4295830359","https://openalex.org/W4299687129","https://openalex.org/W6687241523","https://openalex.org/W6744337509","https://openalex.org/W6747481501","https://openalex.org/W6747615343","https://openalex.org/W6779823015","https://openalex.org/W6781628728","https://openalex.org/W6785015485","https://openalex.org/W6789137956"],"related_works":["https://openalex.org/W2011430815","https://openalex.org/W4321606653","https://openalex.org/W4380433113","https://openalex.org/W4386072068","https://openalex.org/W252339960","https://openalex.org/W2390529043","https://openalex.org/W2378320433","https://openalex.org/W2358343511","https://openalex.org/W2051877971","https://openalex.org/W1970117064"],"abstract_inverted_index":{"Machine":[0],"learning,":[1],"a":[2,53,67,148,162,187,194,214,242,257],"data-driven":[3],"approach,":[4],"is":[5,20],"widely":[6],"used":[7,74],"to":[8,26,84,153,165,197,217,262,265],"automate":[9],"applications.":[10],"It":[11],"has":[12],"been":[13],"observed":[14,104,241],"that":[15],"80%":[16],"of":[17,58,82,86,120,132,151,189,259,272],"the":[18,24,155,168,183,199,211,218,229,232,236],"time":[19,72],"spent":[21],"in":[22,44,70,75,96,127,172,235,245,250],"pre-processing":[23,184],"data":[25,61,79,89,100,121,191,208,251,269],"make":[27],"it":[28],"available":[29],"for":[30,49,52,77,98,231],"building":[31,50],"machine":[32],"learning":[33],"models.":[34],"Data":[35],"scientists":[36],"generally":[37],"develop":[38],"and":[39,123,178,192,227,255],"test":[40],"these":[41,91,133,142],"pipelines,":[42],"primarily":[43],"python":[45],"(a":[46],"popular":[47],"language":[48],"models)":[51],"small":[54],"(in":[55,80],"thousands)":[56],"number":[57],"records":[59,87],"or":[60,88],"points.":[62],"These":[63],"pipelines":[64,92,112],"may":[65],"incur":[66],"non-linear":[68,243],"increase":[69,249],"execution":[71],"when":[73],"production":[76],"large-sized":[78],"10s":[81],"millions":[83],"billions":[85],"points);":[90],"are":[93,134],"not":[94,135],"scalable":[95],"performance":[97,107,170,195,204,246],"larger":[99,207,268],"sizes.":[101,209],"We":[102,224],"have":[103,225],"some":[105,131],"common":[106],"anti-patterns":[108],"across":[109],"many":[110],"ML":[111,115,233],"coded":[113],"by":[114,147],"practitioners,":[116],"such":[117],"as":[118],"abuse":[119],"frames":[122],"nested":[124],"statements,":[125],"especially":[126],"lambda":[128],"functions":[129],"-":[130],"perceivable":[136],"on":[137,186,206,267],"small-sized":[138],"data.":[139],"Once":[140],"recognized,":[141],"patterns":[143],"can":[144],"be":[145],"replaced":[146],"high-performing":[149,215],"piece":[150],"code":[152],"utilize":[154],"underlying":[156],"hardware":[157],"optimally.":[158],"This":[159],"paper":[160],"presents":[161],"framework,":[163],"FASCA,":[164],"automatically":[166],"identify":[167,198],"significant":[169],"bottlenecks":[171],"an":[173,248],"ML/DL":[174],"pipeline":[175,185,234],"using":[176,221],"static":[177],"dynamic":[179],"analysis.":[180],"FASCA":[181,253],"executes":[182],"fraction":[188],"actual":[190],"builds":[193],"model":[196],"top":[200],"bottleneck":[201,219,260],"components":[202,261],"experiencing":[203],"degradation":[205,244],"Further,":[210],"framework":[212],"generates":[213],"alternative":[216],"component":[220],"state-of-the-art":[222],"techniques.":[223],"evaluated":[226],"presented":[228],"results":[230],"Retail":[237],"domain,":[238],"where":[239],"we":[240],"with":[247],"size.":[252],"recommends":[254],"changes":[256],"set":[258],"accelerate":[263],"up":[264],"300%":[266],"size":[270],"(millions":[271],"records).":[273]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}